Intelligent recognition method of radar targets based on mission experience transfer

The meta-learning framework with a multi-class balanced cosine loss and task loss inverse weighted update meta-learner addresses poor radar target recognition accuracy under small samples by decoupling task characteristics and commonalities, enhancing feature separability and balancing category weights for improved recognition.

CN114879185BActive Publication Date: 2024-12-06NAVAL AVIATION UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210668475.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-06-14
Publication Date
2024-12-06
Estimated Expiration
2042-06-14

AI Technical Summary

Technical Problem

Existing radar target recognition methods under small sample conditions suffer from poor multi-category recognition accuracy due to sample imbalance and indiscriminate use of learning experiences, leading to reduced recognition rates, especially for categories with fewer samples.

Method used

A meta-learning framework combining a multi-class balanced center cosine loss base learner and a task loss inverse weighted update meta-learner is employed, decoupling task characteristics from commonalities, using a multi-class balanced cosine loss function to constrain inter-class features and balance category weights, while the meta-learner performs targeted experience transfer through inverse weighted updates.

Benefits of technology

This approach enhances the separability of features, balances category weights, and improves recognition accuracy by avoiding overfitting and excessive reliance on low-relevance experiences, resulting in improved small-sample radar target recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114879185B_ABST
    Figure CN114879185B_ABST
Patent Text Reader

Abstract

The present invention discloses a radar target intelligent recognition method based on task experience transfer, which belongs to the field of radar signal processing. A meta-learning recognition framework combining a multi-class balanced central cosine loss basic learner with a task loss inverse weighted update meta-learner is constructed, and a multi-class balanced cosine center loss function of a convolutional neural network in the basic learner is designed. By introducing Focal loss, the problem of decreased recognition rate of targets of a category with a small number of samples caused by the imbalance of the number of samples of different categories is avoided. Based on the smoothed mean absolute error loss function, a task loss inverse weighted update method for the parameters of the meta-learner is designed, which improves the degree of reference to high-correlation experience, and avoids the problem of non-convergence of the parameter update process caused by the small meta-training task loss value by taking a small operation. The method of the present invention improves the accuracy of multi-category recognition of high-resolution range images of radar targets under small sample conditions, and has popularization and application value.
Need to check novelty before this filing date? Find Prior Art

Description

1. Technical Field

[0001] The invention belongs to the field of radar signal processing, and in particular relates to a radar target intelligent recognition method based on task experience migration. 2. Background Technology

[0002] High Resolution Range Profile (HRRP) is the projection of the main scattering point of the target in the direction of radar illumination. It reflects the relative position information of the target scattering point and, to a certain extent, reflects the partial structural information of the target. It has the advantages of easy storage, easy processing and convenient acquisition, so it has broad application prospects in the field of target recognition. For cooperative targets, a large number of target HRRP samples can be obtained. However, in practical applications, the targets targeted by radar are often non-cooperative targets, and it is difficult to obtain sufficient non-cooperative target HRRP data. Therefore, radar target HRRP recognition under small sample conditions has become one of the research hotspots in the field of radar target recognition.

[0003] In the early days, target classification and recognition technology under small sample conditions was mainly based on the statistical modeling method of HRRP, such as linear dynamic model, factor analysis model and adaptive Gaussian classifier model. Later, scholars used the concept of multi-task learning and category label information to improve on the above models, and successively proposed multi-task factor analysis model, label-assisted factor analysis model and multi-task label-constrained convolution factor analysis model. Statistical modeling methods require prior assumptions on the variables of the model. When the actual environment does not match the prior assumptions, the recognition performance of this type of method will drop sharply.

[0004] In recent years, deep learning methods have received more and more attention in the field of radar target recognition. Deep learning models can autonomously learn the inherent laws and representation levels of data, but they often need to rely on a large amount of sample data and a deeper network structure to obtain the expected recognition effect. In actual adversarial environments, the amount of non-cooperative target data that can be obtained is small and the angle is often relatively single. For the above small sample data, a deep network structure that is too deep in deep learning will lead to model overfitting. To address this problem, relevant scholars, on the one hand, from the perspective of increasing the amount of data, use methods such as generative adversarial networks to enhance data in order to meet the requirements of deep learning models for data sets; on the other hand, they study learning methods based on model transfer, which transfers the model parameters learned in the source domain to the target domain, so as to use the transferred knowledge for small sample recognition. It should be pointed out that in the model transfer method, when the source domain and the target domain are very different, the established transfer model is difficult to apply to different recognition problems. As an extension of the transfer learning method, meta-learning is a mechanism for designing learners with different characteristics for different tasks. It can use the experience of previous different tasks to guide the learning of new tasks. It is suitable for classification, regression, reinforcement learning and other application scenarios. It should be pointed out that existing meta-learning methods often draw on the learning experience of all tasks indiscriminately, ignoring the differential impact of different task experiences on new tasks, which can easily lead to excessive reference to low-relevance experiences, thus causing a decrease in recognition rate. In addition, under small sample conditions, there is often an imbalance in the number of samples between multiple categories. During the back-propagation process, the category with more samples accounts for a higher proportion of the loss function, which can easily guide the model to optimize in a direction that is conducive to outputting the classification results of that category, thereby reducing the recognition rate of targets in the category with fewer samples.

[0005] In order to solve the problem of poor HRRP multi-category recognition accuracy of radar targets under small sample conditions, how to design a suitable basic learner loss function to avoid the problem of decreased recognition rate of targets with fewer samples caused by the imbalance of the number of samples in different categories; and then to conduct targeted transfer and reference of learning experience of different tasks in the meta-learner to guide new recognition tasks to perform effective small sample recognition and improve the subsequent target recognition accuracy, which is one of the difficulties in the field of multi-category small sample intelligent recognition of radar targets. III. Summary of the invention

[0006] 1. Technical problems to be solved

[0007] To address the problem of poor HRRP multi-category recognition accuracy of radar targets under small sample conditions, how to build a suitable meta-learning recognition framework to decouple the characteristics of a single task from the commonalities between tasks, design suitable basic learners and meta-learners to transfer experience between the characteristics of a single task and the commonalities between tasks, and achieve effective small-sample recognition of radar targets; for basic learner construction, how to design a suitable loss function to avoid the problem of decreased recognition rate of targets in categories with fewer samples caused by the imbalance of the number of multi-category samples; for meta-learner construction, how to achieve targeted transfer and reference of learning experience of different tasks to guide new recognition tasks to perform effective small-sample recognition and improve the recognition accuracy of small-sample targets in new tasks.

[0008] 2. Technical solution

[0009] The radar target intelligent recognition method based on task experience transfer of the present invention comprises the following steps:

[0010] Step 1: Constructing the data set for deep meta-learning. Based on the radar high-resolution range image data of N types of targets to be identified, construct a small sample training data set for the meta-test task and a test data set for the meta-test task, and classify the tasks to be identified into the meta-test task set. Based on the accumulated data of M types of non-targets to be identified that are of different categories or different data sources from the target data to be identified, construct a meta-training task set by randomly sampling N types of target data, and use all the N types of non-target data to be identified as the training data set for the meta-training task.

[0011] The meta-learning method specifically includes a neural network adaptation method, a metric learning adaptation method, a basic learner and a meta-learner adaptation method, and a Bayesian meta-learning adaptation method. Among them, the combination of the basic learner and the meta-learner can decouple the task characteristic modeling from the commonality modeling between tasks. Through the mutual communication between the two, the model can achieve the best in both task characteristics and commonality, thereby improving the generalization ability of the model while maintaining the accuracy of the model. The data structure of traditional machine learning is generally divided into a training set and a test set. Both the training set and the test set need to contain a large amount of sample data. Deep meta-learning is similar to traditional machine learning and is also divided into a meta-training set and a meta-test set. The difference is that the meta-training set and the meta-test set are not sample data, but a collection of each task, and each task contains a corresponding training data set and a test data set. Unlike traditional machine learning and classical meta-learning, the data structure of the meta-learning model of the present invention is divided into a meta-training task set and a meta-test task set. The meta-test task set contains corresponding training data sets and test data sets, and in order to improve data utilization, the meta-training task set only contains corresponding training data sets.

[0012] For the recognition task of N types of radar targets, based on the radar high-resolution range image data of the N types of targets to be recognized, a meta-test task small sample training data set and a meta-test task test data set are constructed, that is, the meta-test task training data set is a small sample data set, and the task to be recognized is classified as a meta-test task set; based on M types of non-to-be-recognized targets of different target categories or different data sources from the target data to be recognized, data are accumulated, where M≥N, and a meta-training task set is constructed by randomly extracting N types of target data from the M types. Each meta-training task contains N types of non-to-be-recognized targets, and each meta-training task only contains the meta-training task training data set.

[0013] Different from the classic meta-learning method which divides the meta-training task data into training data set and test data set, the present invention uses all the data in the meta-training task as the meta-training task training data set, thereby improving the training utilization rate of the meta-training task data and the calculation accuracy and stability of the characteristic parameters and loss values ​​of a single meta-training task, which is beneficial to provide more reliable task learning experience for subsequent meta-learners, and is used to guide the precise design of small sample classifiers for targets to be identified.

[0014] It should be emphasized that, in view of the small sample characteristics of the target data to be identified, compared with the radar high-resolution range image data of the N types of targets to be identified, the differences of the accumulated data of the non-to-be-identified targets of the present invention can be reflected in two aspects: either reflected in different target types (for example, the target to be identified is a ship target, and the accumulated data of the non-to-be-identified targets involves aircraft targets); or reflected in different data types (for example, for both being ship targets, the radar high-resolution range image data of the target to be identified is measured data, while the accumulated data of the non-to-be-identified targets is simulated data); or both of the above aspects are different (for example, the radar high-resolution range image data of the target to be identified is measured data, while the non-to-be-identified targets are ground vehicle targets, and their accumulated data are one-dimensional radial sampling data of infrared images or radar high-resolution range image simulation data).

[0015] Step 2: Meta-learning model design; the meta-learning model is designed as a combination of a multi-class balanced center cosine loss base learner and a task loss inverse weighted update meta-learner; the multi-class balanced center cosine loss base learner uses a multi-class balanced cosine center loss function as the convolutional neural network loss function of the meta-training task; the task loss inverse weighted update meta-learner is based on the smoothed mean absolute error loss function and uses the inverse of the meta-training task loss value to perform weighted correction and update on the meta-learner parameters; the input of the meta-learning model is the meta-training task set, and the output of the meta-learning model is the updated model parameters;

[0016] The meta-learning model of the present invention is designed as a combination of a multi-class balanced central cosine loss base learner and a task loss inverse weighted update meta-learner. The basic learner models the task characteristics, and is required to be able to discover the inherent laws of each task data set. The deep learning model relies on a strong representation ability, can extract deep-level features of the target, and has a good degree of fitting to the data. Therefore, for the radar target HRRP multi-class small sample recognition task, the present invention designs a multi-class balanced central cosine loss base learner, using a one-dimensional convolutional neural network (CNN) as a learning and training model; a multi-class balanced cosine center loss function is constructed as the loss function of the one-dimensional CNN, which uses a large edge cosine loss to constrain inter-class features while penalizing features with a large angle with the class center, so that the angular distance of the intra-class features is continuously reduced, and the separability of the features is improved; at the same time, the loss function balances the proportion of each category in the loss function by reducing the weight of the easily distinguishable category in the loss function, avoiding the problem of a decrease in the recognition rate of targets with fewer samples due to the imbalance of the number of samples of different categories.

[0017] The multi-class balanced central cosine loss base learner consists of an input layer, three convolutional layers (Conv), three pooling layers (POOL), a batch normalization layer (BN), two fully connected layers (FC), and an output layer. The specific connection method is:

[0018] Conv1→POOL1→Conv2→POOL2→Conv3+BN→POOL3→FC1→FC2

[0019] Among them, the input layer imports a small batch of data in the training data set of each meta-training task; the first two convolutional layers Conv1 and Conv2 are standard convolutional layers; the third convolutional layer Conv3 is a standardized convolutional layer, and a batch normalization layer BN is added on the basis of the convolutional layer Conv3 to enhance the gradient change of the multi-class balanced cosine center loss function. The three convolutional layers all use one-dimensional convolution kernels with sizes of A1, A2 and A3 respectively, numbers of B1, B2 and B3 respectively, step length of D, and the filling method is the same filling; the pooling layer POOL is an average pooling layer with a step length of H; the number of neurons in the first fully connected layer FC1 is F, and the number of neurons in the second fully connected layer FC2 is equal to the number of target categories to be identified N; the output layer uses the softmax function to calculate the category probability of each sample, and calculates the loss function value based on the calculation results.

[0020] Under the condition of small samples, there is often an imbalance in the number of samples between multiple categories. In the back propagation process, the category with more samples accounts for a higher proportion of the loss function, which is easy to guide the model to optimize in the direction that is conducive to outputting the classification results of this category, thereby reducing the recognition rate of the target of the category with fewer samples. To this end, the present invention constructs a multi-class balanced cosine center loss function in the CNN of the basic learner, calculates the Focal loss based on the cosine distance and the feature center, and uses the enhanced edge cosine loss to constrain the inter-class features while penalizing the features with a larger angle with the class center, so that the angular distance of the intra-class features is continuously reduced, and the separability of the features is improved; at the same time, the loss function reduces the weight of the easily distinguishable category in the loss function by introducing the Focal loss, so as to balance the proportion of each category in the loss function, and avoids the problem of reduced recognition rate of the target of the category with fewer samples caused by the imbalance of the number of samples of different categories.

[0021] The loss function of each meta-training task can be expressed as:

[0022]

[0023] Among them, m is the number of sample data in the gradient update process; x i Represents the fully connected layer output feature vector corresponding to the i-th sample; y i is the true label of the i-th sample; W j is the j-th column of the weight matrix W of the fully connected layer, which represents the weight vector corresponding to the j-th type of target; Indicates the yth i The normalized feature center vector of the class target; log2(·) represents the logarithmic function with base 2; a, λ, s, α, and γ are positive real parameters; among them, the positive parameter a satisfies 0≤a≤1-cos(2π / N), and its role is to enhance the feature vector x i With the y i The weight vector corresponding to the class target The angle constraint of ; the real parameter s solves the problem of non-convergence of the loss function and satisfies ε is a positive constant close to 0; the positive parameter γ is used to adjust the output weight, satisfying 0≤γ≤5; the real parameter α is used to adjust the normalized feature amplitude in the central loss term to prevent the problem of non-convergence of the loss function after feature normalization; the positive parameter λ is the weight of the central loss term, satisfying λ>0. The larger λ is, the more clustered the features within the class are; φ (·,·) Represents the angle between two vectors of the same dimension.

[0024] If the angle between two vectors x and y is φ (x,y) , then the cosine distance between two vectors x and y is the cosine value of the angle between them, which can be expressed as the inner product of the normalized vectors cos(φ (x,y))=x T y / (||x||||y||), the superscript T represents transpose, ||·|| represents taking the Euclidean norm, and the cosine distance can effectively avoid the adverse effect of the module values ​​of different vectors on the distance measurement. is the weight vector W j and the eigenvector x i The similarity measure between them is that the cosine of the angle is The interval is monotonically decreasing. The smaller the angle between the vectors, the larger the cosine value. The eigenvector x i The greater the probability that the corresponding i-th sample belongs to category j, the greater the probability that the corresponding i-th sample belongs to category j. In order to further increase the inter-class distance of target features of different categories, the present invention introduces a hyperparameter a. When When , the i-th sample is determined to belong to category j. The role of the hyperparameter a is to enhance the feature vector x i With weight vector Angle constraint.

[0025] The normalized feature center vector c of the j-th target j The initialization can be expressed as

[0026]

[0027] Where δ[·] represents the unit impulse sequence function. When x = 0, δ[x] is equal to 1, otherwise δ[x] is equal to 0. During the training process, the normalized feature center vector c of the j-th target j The update amount is:

[0028]

[0029] The meta-learner in the meta-learning model design mainly models the commonalities between tasks. Its function is to summarize the training experience on all tasks after each basic learner training is completed, synthesize new experience, and feed it back to the basic learner. The meta-learner comes in various forms and can be any model based on stochastic gradient descent or a parameter update algorithm. In order to reduce the computational complexity and improve the accuracy and efficiency of parameter updates, the method of the present invention designs a task loss inverse weighted update meta-learner. Based on the smoothed mean absolute error loss function, the inverse of the meta-training task loss value is used to perform weighted correction and update on the meta-learner parameters. By fully considering the differential impact of different task experiences on new tasks, the learning experience of different meta-training tasks is specifically referenced, avoiding the problem of reduced recognition rate due to excessive reference to low-relevance experience, so that the initialization model parameter θ of the meta-learner is M Update towards the common direction of highly related tasks.

[0030] The main purpose of meta-learning is to find the common direction of highly related tasks so that the initialization model parameters θ of the meta-learner M Close to the characteristic parameters of the highly relevant meta-training tasks in the base learner, that is, the parameter θ M Minimize the error distance between all meta-training task characteristic parameters, that is, the learning objective function of the meta-learner is as follows

[0031]

[0032] Among them, D k is the characteristic parameter θ of the kth meta-training task Bk and the meta-learner parameters θ M Different from the commonly used meta-learner objective function design, the inequality measure is ignored in formula (4), and only the main error term is retained. On the basis of ensuring the accuracy of parameter update, the difficulty of subsequent gradient solution and the computational complexity of meta-learner parameter update are reduced, and the parameter update efficiency is improved.

[0033] In order to prevent the gradient explosion problem of the mean square error (corresponding to the Euclidean space distance) and avoid the non-smooth gradient defect of the mean absolute error at zero, the method of the present invention constructs a smooth mean absolute error loss function. k Specifically expressed as

[0034]

[0035] The learning goal of the meta-learner is to minimize the error between the parameters of the two learners. According to Lagrange’s theorem, D can be calculated k In the parameter θ M The gradient at D is minimized k For ||θ Bk -θ M ||<1, for distance D k Taking the derivative we get:

[0036]

[0037] Meta-learners often assume that each meta-training task has an effect on the meta-learner parameters θ M The influence of each task on the meta-learner parameter θ is the same. M The influence of is indifferently superimposed to calculate the common direction of all tasks. Considering the differential influence of different meta-training task experiences on new tasks, the task loss value L of the kth meta-training task is kIt can reflect the degree of difference in learning experience to a certain extent. The smaller the loss value, the larger its reciprocal, which means the better the training effect, that is, the learning experience of this task is more worthy of reference; on the contrary, the larger the loss value, the smaller its reciprocal, which means the worse the learning effect of the meta-training task, and the lower the reference degree of learning experience. Therefore, in order to avoid excessive reference to low-relevance experience and make full use of the bias influence of different meta-training tasks on the parameter update of the meta-learner, the method of the present invention uses the reciprocal of the loss value of the meta-training task to perform weighted correction on the parameter update process of the meta-learner, so that the meta-learner can draw on the experience of each meta-training task in a targeted manner, reduce excessive reference to low-relevance experience, and improve the degree of reference to high-relevance experience. The parameter update method of the meta-learner weighted by the reciprocal of the task loss is as follows:

[0038]

[0039] in, is the updated parameter of the meta-learner, ε0 is the update step of the meta-learner; the task loss value L k The reciprocal of L k The change of is directly negatively correlated, and the weighted update method is intuitive and concise. Considering the function convergence problem in the parameter update process, min(·,·) means taking the smaller value of the two parameters, which is used to prevent L k If the value is too small, the parameter update process will not converge.

[0040] Step 3 randomly selects K meta-training tasks from the meta-training task set to train the base learner; for the kth meta-training task, the meta-training task training data set is used for batch training on the multi-class balanced central cosine loss base learner, and the characteristic parameter θ of the kth meta-training task is obtained through iterative update optimization of the convolutional neural network. Bk And the loss value L k ; Pass the characteristic parameters and loss values ​​of the K meta-training tasks forward to the task loss inverse weighted update meta-learner, and go to step 4;

[0041] K meta-training tasks are randomly selected from the meta-training task set for basic learner training; for the kth meta-training task, the multi-class balanced central cosine loss basic learner designed in step 2 is used to perform batch training in combination with the training data set of the kth meta-training task. According to the multi-class balanced cosine central loss function of formula (1), the convolutional neural network is used for iterative update optimization training to obtain the characteristic parameter θ of the kth meta-training task. Bk and the corresponding task loss value L k ; After all K meta-training tasks have completed the basic learner training, the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θBK} and the corresponding task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}Forward pass to the task loss inverse weighted update meta-learner, and go to step 4 to update the meta-learner parameters.

[0042] Step 4: Update the meta-learner with the inverse of the task loss based on the characteristic parameters of the K meta-training tasks, and use the inverse of the corresponding meta-training task loss value to update the meta-learner parameter θ M Perform weighted correction update and update the updated parameters Feedback to the multi-class balanced center cosine loss base learner; Initialize the model parameters of the multi-class balanced central cosine loss base learner and re-execute step 3 for a new round of optimization training;

[0043] The inverse of the task loss weighted update meta-learner is based on the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θ BK}, using the corresponding meta-training task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}, based on formula (7) for the meta-learner parameter θ M Perform weighted correction update and update the updated parameters Feedback to the multi-class balanced center cosine loss base learner; Initialize the model parameters of the multi-class balanced central cosine loss base learner and re-execute step 3 for a new round of optimization training;

[0044] Step 5: Repeat steps 3 and 4 until N is reached. c At the end of the cycle, save the inverse of the last task loss and weight the update meta-learner parameters Construct a convolutional neural network recognition model with the same model structure as the multi-class balanced central cosine loss base learner. As the initialization parameters of the convolutional neural network recognition model, the small sample training data set of the meta-test task is imported in batches to train and update the recognition model. The recognition model training is terminated when the multi-class balanced cosine center loss function of the convolutional neural network converges and no longer decreases. The trained convolutional neural network recognition model is used to classify and recognize the meta-test task test data set, and the classification and recognition accuracy of the N types of targets to be identified is evaluated.

[0045] The meta-learning training phase is structurally divided into two loop structures, the inner loop refers to the cyclic update of parameters between the base learner and the meta-learner, and the outer loop refers to the training round cycle of the inner loop. First, the model parameters of the base learner are initialized, and the recognition tasks are extracted from the meta-training set and imported into the base learner for learning. The base learner parameters are updated according to the multi-class balanced cosine center loss function; secondly, the model parameters learned by the base learner are imported into the meta-learner for parameter update by weighted update of the inverse of the task loss, and the updated parameters are fed back to the base learner for re-assignment of parameters, and a new round of meta-training task extraction and base learner training is carried out. The cycle is repeated until the outer loop number is reached and the final CNN model parameters are saved.

[0046] The meta-learning test phase uses the training parameters of the meta-learning training phase to initialize the parameters of the recognition model, so as to transfer the previous learning experience to the meta-test set, and use the initialized recognition model for classification and recognition to verify the effectiveness of the method. First, the CNN model parameters saved in the meta-learning training phase are used as the initial parameters of the recognition model, and the small sample training data set in the meta-test set is imported to train the recognition model until the multi-class balanced cosine center loss function converges, and the meta-test set training is terminated; then, the recognition model and parameters obtained from the meta-test set training are used to classify and recognize the test data set of the meta-test set, and the classification and recognition accuracy of each type of target in the test data set is calculated.

[0047] 3. Beneficial effects

[0048] Compared with the background technology, the beneficial effects of the present invention are: 1) In order to solve the problem of poor multi-category recognition accuracy of radar target HRRP under small sample conditions, a meta-learning recognition framework of a multi-class balanced central cosine loss basic learner combined with a task loss inverse weighted update meta-learner is constructed to decouple the characteristics of a single task from the commonalities between tasks, and to transfer experience between the characteristics of a single task and the commonalities between tasks, so as to achieve small-sample effective recognition of radar target HRRP; 2) For the CNN construction of the basic learner, a multi-class balanced cosine center loss function is designed, and the enhanced marginal cosine loss is used to constrain the inter-class features to improve the separability of inter-class features. At the same time, the features with a large angle with the class center are penalized, which improves the aggregation of intra-class features and further enhances the overall separability of features; 3) The multi-class balanced cosine center loss function introduces the focal loss to reduce the weight of the easily distinguishable category in the loss function, balance the proportion of each category in the loss function, and avoid the imbalance caused by the imbalance of the number of samples of different categories. The problem of decreased recognition rate of targets in categories with a small number of samples is caused; 4) A meta-learner learning objective function containing only the main error term is constructed. By ignoring the inequality metrics with low influence, the difficulty of subsequent gradient solution and the computational complexity of meta-learner parameter update are reduced on the basis of ensuring the accuracy of parameter update, thereby improving the efficiency of parameter update; 5) A smoothed mean absolute error loss function of the meta-learner is constructed to avoid the gradient explosion problem of the mean square error, overcome the non-smooth gradient defect of the mean absolute error at zero, improve the modeling accuracy of the error term of the meta-learner objective function, and provide a model guarantee for the efficient update of the subsequent meta-learner parameters; 6) A task loss inverse weighted update method for the meta-learner parameters is designed. The negative correlation between the meta-training task loss value and the task training effect is used to avoid excessive reference to low-correlation experience and improve the degree of reference to high-correlation experience. By taking the small operation, the problem of non-convergence of the parameter update process caused by the small meta-training task loss value is avoided. IV. Description of the drawings

[0049] Figure 1 It is a schematic diagram of the meta-learning data structure of the method of the present invention;

[0050] Figure 2 It is a schematic diagram of the structure of the meta-learning model of the method of the present invention;

[0051] Figure 3 This is a schematic diagram of the structure of the basic learner of the method of the present invention.

[0052] Figure 4 This is a flow chart of the radar target intelligent recognition method based on task experience transfer V. Specific implementation methods

[0053] The present invention is further described below in conjunction with the accompanying drawings. The embodiments of the present invention are used to explain the present invention, rather than to limit the present invention. Within the spirit of the present invention and the protection scope of the claims, any modifications and changes made to the present invention fall within the protection scope of the present invention.

[0054] To verify the effectiveness of the method described in the present invention, this specific implementation method provides two examples. The first example is for the HRRP recognition application of multiple types of ship target radars, and the second example is for the HRRP recognition application of multiple types of aircraft target radars.

[0055] Embodiment 1:

[0056] Example 1 is an application of radar HRRP recognition of five types of ship targets, which can be specifically divided into the following steps:

[0057] Step A-1: ​​Construct a deep meta-learning dataset, whose meta-learning data structure is as follows Figure 1 As shown in the figure; firstly, the simulation data of HRRP of M=10 types of ship targets are obtained, and the meta-training task set is constructed by randomly extracting N=5 types of target data, and all the simulation data of N types of non-to-be-identified ship targets are used as the meta-training task training data set; in view of the non-cooperation of ship targets in actual experiments, only a small number of small sample HRRP measured data of ship targets to be identified can be obtained. According to the radar measured HRRP data of N types of ship targets to be identified, the small sample training data set of the meta-test task and the test data set of the meta-test task are constructed, and the task to be identified is classified into the meta-test task set.

[0058] Step A-2: Design a meta-learning model; the meta-learning model is designed as a combination of a multi-class balanced central cosine loss base learner and a task loss inverse weighted update meta-learner. The model structure is as follows: Figure 2 As shown. The multi-class balanced center cosine loss base learner uses the multi-class balanced cosine center loss function as the convolutional neural network loss function of the meta-training task; the task loss inverse weighted update meta-learner is based on the smoothed mean absolute error loss function, and uses the inverse of the meta-training task loss value to perform weighted correction and update on the meta-learner parameters; the input of the meta-learning model is the meta-training task set, and the output of the meta-learning model is the updated model parameters;

[0059] Step A-3: extract 5 types of target data from the simulation data of HRRP of 10 types of ship targets without duplication to form a set of 252 meta-training tasks, and randomly extract K=10 meta-training tasks from the meta-training task set to train the basic learner;

[0060] CNN model parameters θ for multi-class balanced central cosine loss based learner B Initialize, including the weights of the convolutional layer {w conv1 ,bconv1 ,w conv2 ,b conv2 , w conv3 ,b conv3}, the weights of the fully connected layer {w fc ,b fc ,w fc2 ,b fc2 The structural parameters of the multi-class balanced central cosine loss base learner are: N = 5, A1 = 9, A2 = 9, A3 = 9, B1 = 8, B2 = 16, B3 = 32, D = 1, H = 2, F = 100; the specific design of the corresponding multi-class balanced central cosine loss base learner is as follows Figure 3 shown.

[0061] For the kth meta-training task, the multi-class balanced central cosine loss basic learner is used to perform batch training in combination with the training data set of the kth meta-training task. According to the multi-class balanced cosine central loss function of the convolutional neural network in formula (1), the Adam optimizer is used to iteratively optimize and update the parameters, and then the characteristic parameter θ of the kth meta-training task is obtained. Bk and the corresponding task loss value L k ; After all K meta-training tasks have completed the basic learner training, the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θ BK} and the corresponding task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}Forward pass to the task loss inverse weighted update meta-learner, and go to step A-4 to update the meta-learner parameters.

[0062] Step A-4: Update the meta-learner based on the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θ BK}, using the corresponding meta-training task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}, based on formula (7) for the meta-learner parameter θ M Perform weighted correction update and update the updated parameters Feedback to the multi-class balanced central cosine loss base learner in step A-3; The newly initialized model parameters of the multi-class balanced central cosine loss base learner are re-executed in step A-3 for a new round of optimization training;

[0063] Step A-5: The process of the radar target intelligent recognition method based on task experience transfer is as follows: Figure 4 According to the processing flow, step A-3 and step A-4 are executed repeatedly until N is reached. c = 25 cycles are completed and the final meta-learner parameters are saved Based on the multi-class balanced central cosine loss basic learner, a CNN recognition model with the same model structure is constructed. As the initialization parameters of the CNN recognition model, the small sample training data set of the meta-test task is imported in batches to train and update the model. The model training is terminated when the multi-class balanced cosine center loss function of CNN converges and no longer decreases. The trained CNN recognition model is used to classify and recognize the meta-test task test data set, and the classification and recognition accuracy of the measured data of the five types of ship targets to be identified is evaluated.

[0064] The experimental analysis results show that compared with the CNN model, the deep transfer learning model (DTL) and the meta-learning model with unbiased reference to task experience (UBML), the task loss inverse weighted update meta-learning model designed in the present invention has greatly improved the recognition performance of the measured HRRP of multiple types of ship targets under small sample conditions by making differentiated and targeted use of previous experiences in different simulated ship target recognition tasks. Under the condition of small sample, the CNN model is directly trained and tested from beginning to end. Due to the reduction of training data, the CNN network is prone to overfitting and poor recognition rate; DTL can only transfer single task characteristics, and its recognition is limited by the experience quality of a single source task, and the recognition effect of small samples is poor; UBML indiscriminately borrows the learning experience of the meta-training task, and can perform more accurate classification and recognition through the migration of task common experience, but excessive borrowing of low-correlation experience leads to poor recognition rate of small samples of ship targets, and it is difficult to avoid the reduction of recognition rate of targets with fewer samples caused by the imbalance of sample numbers of different categories of targets; the task loss inverse weighted update meta-learning model designed by the present invention performs task loss inverse weighted correction on learning experience of different tasks in the meta-learner, guides new recognition tasks to perform effective small sample recognition, and improves the overall recognition accuracy of small sample recognition of ship targets. In summary, the method of the present invention is better than other existing learning models as a whole, and is more suitable for classification and recognition of small sample ship targets than previous transfer learning methods, which reflects the superiority of the method of the present invention.

[0065] Embodiment 2:

[0066] Example 2 is an application of radar HRRP recognition of four types of aircraft targets, which can be specifically divided into the following steps:

[0067] Step B-1: Construct a deep meta-learning dataset, whose meta-learning data structure is as follows Figure 1 As shown in the figure. Due to the lack of simulation models for aircraft targets, the accumulated measured HRRP data of ground vehicle targets can be used to construct meta-learning training tasks. First, the measured HRRP data of M = 8 types of vehicle targets are obtained, and the meta-training task set is constructed by randomly extracting N = 4 types of target data, and all the measured data of N types of non-identified vehicle targets are used as the meta-training task training data set; in view of the non-cooperativeness of actual test aircraft targets, only a small number of small sample HRRP measured data of aircraft targets to be identified can be obtained. Based on the radar measured HRRP data of N types of aircraft targets to be identified, a small sample training data set of the meta-test task and a test data set of the meta-test task are constructed, and the task to be identified is classified as the meta-test task set.

[0068] Step B-2: Design a meta-learning model; the meta-learning model is designed as a combination of a multi-class balanced central cosine loss base learner and a task loss inverse weighted update meta-learner. The model structure is as follows: Figure 2 As shown. The multi-class balanced center cosine loss base learner uses the multi-class balanced cosine center loss function as the convolutional neural network loss function of the meta-training task; the task loss inverse weighted update meta-learner is based on the smoothed mean absolute error loss function, and uses the inverse of the meta-training task loss value to perform weighted correction and update on the meta-learner parameters; the input of the meta-learning model is the meta-training task set, and the output of the meta-learning model is the updated model parameters;

[0069] Step B-3: extract 4 types of target data from the measured data of HRRP of 8 types of vehicle targets without duplication to form a set of 70 meta-training tasks, and randomly extract K=10 meta-training tasks from the meta-training task set to train the basic learner;

[0070] CNN model parameters θ for multi-class balanced central cosine loss based learner B Initialize, including the weights of the convolutional layer {w conv1 ,b conv1 ,w conv2 ,b conv2 , w conv3 ,b conv3}, the weights of the fully connected layer {w fc ,b fc ,w fc2 ,b fc2 The structural parameters of the multi-class balanced central cosine loss base learner are: N = 5, A1 = 9, A2 = 9, A3 = 9, B1 = 8, B2 = 16, B3 = 32, D = 1, H = 2, F = 100; the specific design of the corresponding multi-class balanced central cosine loss base learner is as follows Figure 3 shown.

[0071] For the kth meta-training task, the multi-class balanced central cosine loss basic learner is used to perform batch training in combination with the training data set of the kth meta-training task. According to the multi-class balanced cosine central loss function of the convolutional neural network in formula (1), the Adam optimizer is used to iteratively optimize and update the parameters, and then the characteristic parameter θ of the kth meta-training task is obtained. Bk and the corresponding task loss value L k ; After all K meta-training tasks have completed the basic learner training, the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θ BK} and the corresponding task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}Forward pass to the task loss inverse weighted update meta-learner, and go to step B-4 to update the meta-learner parameters.

[0072] Step B-4: Update the meta-learner based on the characteristic parameters {θ B1 ,θ B2 ,…,θ Bk ,…,θ BK}, using the corresponding meta-training task loss value {L B1 ,L B2 ,…,L Bk ,…,L BK}, based on formula (7) for the meta-learner parameter θ M Perform weighted correction update and update the updated parameters Feedback to the multi-class balanced central cosine loss base learner in step B-3; The newly initialized model parameters of the multi-class balanced central cosine loss base learner are re-executed in step B-3 for a new round of optimization training;

[0073] Step B-5: The process of the radar target intelligent recognition method based on task experience transfer is as follows Figure 4 According to the processing flow, step B-3 and step B-4 are executed repeatedly until N is reached. c =7 cycles end, save the final meta-learner parameters Based on the multi-class balanced central cosine loss basic learner, a CNN recognition model with the same model structure is constructed. As the initialization parameters of the CNN recognition model, the small sample training data set of the meta-test task is imported in batches to train and update the model. The model training is terminated when the multi-class balanced cosine center loss function of CNN converges and no longer decreases. The trained CNN recognition model is used to classify and recognize the meta-test task test data set, and the classification and recognition accuracy of the measured data of the four types of aircraft targets to be identified is evaluated.

[0074] The experimental analysis results show that compared with the CNN model, the deep transfer learning model (DTL) and the meta-learning model with unbiased reference to task experience (UBML), the task loss inverse weighted update meta-learning model designed in the present invention has greatly improved the recognition performance of the measured HRRP of multiple types of aircraft targets under small sample conditions by making differentiated and targeted transfer of previous different measured vehicle target recognition task experiences. Under the condition of small sample, the CNN model is directly trained and tested from beginning to end. Due to the reduction of training data, the CNN network is prone to overfitting and poor recognition rate; DTL can only transfer single task characteristics, and its recognition is limited by the experience quality of a single source task, and the recognition effect of small samples is poor; UBML indiscriminately borrows the learning experience of the meta-training task, and can perform more accurate classification and recognition through the migration of task common experience, but excessive borrowing of low-correlation experience leads to poor recognition rate of small samples of aircraft targets, and it is difficult to avoid the reduction of recognition rate of targets with fewer samples caused by the imbalance of sample numbers of different categories of targets; the task loss inverse weighted update meta-learning model designed by the present invention performs task loss inverse weighted correction on learning experience of different tasks in the meta-learner, guides new recognition tasks to perform effective small sample recognition, and improves the overall recognition accuracy of small sample recognition of aircraft targets. In summary, the method of the present invention is better than other existing learning models as a whole, and is more suitable for classification and recognition of small sample aircraft targets than previous transfer learning methods, which reflects the superiority of the method of the present invention.

Claims

1. A radar target intelligent recognition method based on task experience transfer, characterized in that: The following steps are involved: Step 1: Constructing the data set for deep meta-learning. Based on the radar high-resolution range image data of N types of targets to be identified, construct a small sample training data set for the meta-test task and a test data set for the meta-test task, and classify the tasks to be identified into the meta-test task set. Based on the accumulated data of M types of non-targets to be identified that are of different categories or different data sources from the target data to be identified, construct a meta-training task set by randomly sampling N types of target data, and use all the N types of non-target data to be identified as the training data set for the meta-training task. Step 2: Meta-learning model design; the meta-learning model is designed as a combination of a multi-class balanced center cosine loss base learner and a task loss inverse weighted update meta-learner; the multi-class balanced center cosine loss base learner uses a multi-class balanced cosine center loss function as the convolutional neural network loss function of the meta-training task; the task loss inverse weighted update meta-learner is based on the smoothed mean absolute error loss function and uses the inverse of the meta-training task loss value to perform weighted correction and update on the meta-learner parameters; The input of the meta-learning model is the meta-training task set, and the output of the meta-learning model is the updated model parameters; In the construction of the convolutional neural network of the multi-class balanced center cosine loss base learner, a multi-class balanced cosine center loss function is designed. The focal loss is calculated based on the cosine distance and the feature center. The loss function of each meta-training task is specifically expressed as Among them, m is the number of sample data in the gradient update process; x i Represents the fully connected layer output feature vector corresponding to the i-th sample; y i is the true label of the i-th sample; W j is the weight vector corresponding to the j-th target; c yi Indicates the yth i The normalized feature center vector of the class target; a, λ, s, α and γ are positive real parameters; φ (.,·) Represents the angle between two vectors of the same dimension; The normalized feature center vector c of the j-th target j The initialization can be expressed as During the training process, c j The update amount is Where, δ[·] represents the unit impulse sequence function; The main error term in the learning objective function of the task loss inverse weighted update meta-learner is designed as a smoothed mean absolute error loss function, and the characteristic parameter θ of the kth meta-training task is Bk and the meta-learner parameters θ M The error between k Expressed as Among them, ||·|| means taking the Euclidean norm; The parameter update method of the task loss inverse weighted update meta-learner is in, is the updated parameter of the meta-learner, and min(·,·) means taking the smaller value of the two parameters; Step 3 randomly selects K meta-training tasks from the meta-training task set to train the base learner; for the kth meta-training task, the meta-training task training data set is used for batch training on the multi-class balanced central cosine loss base learner, and the characteristic parameter θ of the kth meta-training task is obtained through iterative update optimization of the convolutional neural network. Bk And the loss value L k ; Pass the characteristic parameters and loss values ​​of the K meta-training tasks forward to the task loss inverse weighted update meta-learner, and go to step 4; Step 4: Update the meta-learner with the inverse of the task loss based on the characteristic parameters of the K meta-training tasks, and use the inverse of the corresponding meta-training task loss value to update the meta-learner parameter θ M Perform weighted correction update and update the updated parameters Feedback to the multi-class balanced center cosine loss base learner; Initialize the model parameters of the multi-class balanced central cosine loss base learner and re-execute step 3 for a new round of optimization training; Step 5: Repeat steps 3 and 4 until N is reached. c At the end of the cycle, save the inverse of the last task loss and weight the update meta-learner parameters Construct a convolutional neural network recognition model with the same model structure as the multi-class balanced central cosine loss base learner. As the initialization parameters of the convolutional neural network recognition model, the small sample training data set of the meta-test task is imported in batches to train and update the recognition model. The recognition model training is terminated when the multi-class balanced cosine center loss function of the convolutional neural network converges and no longer decreases. The trained convolutional neural network recognition model is used to classify and recognize the meta-test task test data set, and the classification and recognition accuracy of the N types of targets to be identified is evaluated.