Training method and apparatus for integrated network based on modular auto-encoding

Abstract

The application discloses a training method and device of an integrated network based on modular self-encoding, and belongs to the technical field of artificial intelligence. The training method comprises the following steps: acquiring training data, training a convolutional network self-encoder based on the training data by using an isometric constraint, and obtaining a trained self-encoder; inputting an image I in the training data into the trained self-encoder to obtain f (i) ; accessing the obtained f (i) into a base model G (i) , and obtaining G (i) (f (i) ); training an integrated learning model E by using G (i) (f (i) ), and obtaining a trained base model G (i) and the integrated learning model E. The application firstly trains a modular self-encoder by constructing an isometric constraint, promotes the specialization of network module functions. Then, the functional differentiation characteristic module and the base model are used for integrated learning, the homogenization problem among the integrated learning base models is reduced, and the generalization ability, the robustness and the integrated effect of the integrated learning are improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a training method and apparatus for an integrated network based on modular autoencoders. Background Technology

[0002] Ensemble learning is a machine learning method that combines multiple learners (called base learners) to achieve better performance than a single learner. Compared to a single learner, ensemble learning reduces overfitting of the model to the training data and improves the model's generalization ability by combining the predictions of multiple different learners. Different base learners may make different mistakes; by integrating the predictions of multiple learners, the probability of a single learner making a mistake can be reduced, improving the accuracy of the overall model. When there are outliers in the dataset, a single learner may be misled by these outliers, while ensemble learning can mitigate the impact of these outliers. Ensemble learning is simple to implement while improving generalization ability and robustness, and it can be combined with any base model, offering good flexibility.

[0003] However, ensemble learning is also prone to homogeneity issues, meaning that the capabilities of each base model are too similar. This leads to poor ensemble performance, sometimes even worse than that of a single base learner. Since homogeneous base learners often make similar mistakes, ensemble learning cannot effectively compensate for these errors; instead, it amplifies their impact. Therefore, reducing the homogeneity between base models is crucial for improving ensemble performance in ensemble learning. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the present invention provides the following technical solution.

[0005] The first aspect of this invention provides a training method for an ensemble network based on a modular autoencoder, comprising:

[0006] Acquire training data, which includes image I and image I′ obtained by transforming image I;

[0007] Based on the training data, the convolutional network autoencoder is trained using equivariant constraints to obtain a trained autoencoder; wherein, the equivariant constraint L... EC The following formula is used for calculation:

[0008]

[0009] L equ =∑ i ||f′ (i) -M (i) (δ)f (i) ||2 , i∈{0,1,...,k-1},

[0010]

[0011] L EC =L recon +λ1L equ +λ2L sym ,

[0012] f = I * W,

[0013] f′=I′*W,

[0014] Where, I′=L δ (I), where Lδ is a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) f′ (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i) (δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC For equivariant constraints; λ1 and λ2 are the weighting coefficients of equivariant loss and symmetric loss, respectively; l represents the number of dimensions of each module; This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. (i) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′(i) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms;

[0015] The image I from the training data is input into the trained autoencoder to obtain the feature maps f of each module. (i) , i = 0, 1, 2, ..., k-1; for each feature map f obtained (i) Access a base model G (i) In the middle, the output result G is obtained. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and ensemble learning model E;

[0016] The trained autoencoder and base model G (i) Together with the ensemble learning model E, they form an ensemble network based on modular autoencoders.

[0017] Preferably, the transformation includes a translation transformation or a translation-rotation transformation.

[0018] A second aspect of the present invention provides an integrated network based on modular autoencoders, trained using the method described in the first aspect.

[0019] A third aspect of the present invention provides a training apparatus for an ensemble network based on a modular autoencoder, comprising:

[0020] The training data acquisition module is used to acquire training data, which includes image I and image I′ obtained by transforming image I;

[0021] The autoencoder training module is used to train the convolutional network autoencoder based on the training data using equivariant constraints, thereby obtaining a trained autoencoder; wherein, the equivariant constraint L... EC The following formula is used for calculation:

[0022]

[0023] L equ =∑ i ||f′ (i) -M (i) (δ)f (i) || 2 , i∈{0,1,...,k-1},

[0024]

[0025] L EC =L recon +λ1L equ +λ2L sym ,

[0026] f = I * W,

[0027] f′=I′*W,

[0028] Where, I′=L δ (I), where Lδ is a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) f′ (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i) (δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC For equivariant constraints; λ1 and λ2 are the weighting coefficients of equivariant loss and symmetric loss, respectively; l represents the number of dimensions of each module; This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. (i) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′ (i) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms;

[0029] The base model and ensemble learning model training module is used to input the image I from the training data into the trained autoencoder to obtain the feature maps f of each module. (i) , i = 0, 1, 2, ..., k-1; for each feature map f obtained (i) Access a base model G (i) In the middle, the output result G is obtained. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and ensemble learning model E;

[0030] The modular autoencoder-based ensemble network is used to construct modules for training the autoencoder and the base model G. (i) Together with the ensemble learning model E, they form an ensemble network based on modular autoencoders.

[0031] Preferably, the transformation includes a translation transformation or a translation-rotation transformation.

[0032] A fourth aspect of the present invention provides a memory that stores a plurality of instructions for implementing the training method of the modular autoencoder-based integrated network as described in the first aspect.

[0033] A fifth aspect of the present invention provides an electronic device including a processor and a memory connected to the processor, the memory storing a plurality of instructions which can be loaded and executed by the processor to enable the processor to perform a training method for an integrated network based on a modular autoencoder as described in the first aspect.

[0034] The beneficial effects of this invention are as follows: The training method and apparatus for ensemble networks based on modular autoencoders provided by this invention first construct equivariant constraints and then use these constraints to train the modular network autoencoder on training data of homologous image pairs, obtaining a trained autoencoder. This enhances the correlation within the autoencoder modules and the independence between modules, promoting the specialization of network module functions. Then, functionally differentiated feature modules and base models are used for ensemble learning. Due to the functional differentiation between modules, the homogenization problem between base models in ensemble learning can be greatly reduced, thereby improving the generalization ability, robustness, and ensemble effect of ensemble learning. Attached Figure Description

[0035] Figure 1This is a schematic diagram of the training method for the modular autoencoder-based ensemble network described in this invention.

[0036] Figure 2 This is a schematic diagram of the training process of a modular autoencoder.

[0037] Figure 3 This is a schematic diagram of the training process of an ensemble network based on modular autoencoders.

[0038] Figure 4 This is a schematic diagram illustrating the functional differentiation effect under modular and equivariant constraints.

[0039] Figure 5 This is a schematic diagram of the functional structure of the training device based on the modular autoencoder integrated network described in this invention. Detailed Implementation

[0040] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0041] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a memory, and a display screen. The memory stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0042] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in memory, and by calling data stored in memory.

[0043] Memory can include random access memory (RAM) or read-only memory (ROM). Memory can be used to store instructions, programs, code, code sets, or instructions.

[0044] The display screen is used to show the user interface of each application.

[0045] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0046] Example 1

[0047] like Figure 1As shown, this embodiment of the invention provides a training method for an ensemble network based on a modular autoencoder, comprising:

[0048] S101, Obtain training data, the training data including image I and image I′ obtained by transforming image I;

[0049] S102, Based on the training data, the convolutional network autoencoder is trained using equivariant constraints to obtain a trained autoencoder; wherein, the equivariant constraint L EC The following formula is used for calculation:

[0050]

[0051] L equ =∑ i ||f′ (i) -M (i) (δ)f (i) || 2 , i∈{0,1,...,k-1},

[0052]

[0053] L EC =L recon +λ1L equ +λ2L sym ,

[0054] f = I * W,

[0055] f′=I′*W,

[0056] Where, I′=L δ (I), where Lδ is a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) f′ (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i)(δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC For equivariant constraints; λ1 and λ2 are the weighting coefficients of equivariant loss and symmetric loss, respectively; l represents the number of dimensions of each module; This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. (i) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′ (i) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms;

[0057] S103, Input the image I from the training data into the trained autoencoder to obtain the feature maps f of each module. (i) , i = 0, 1, 2, ..., k-1; for each feature map f obtained (i) Access a base model G (i) In the middle, the output result G is obtained. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and ensemble learning model E;

[0058] S104, the trained autoencoder and base model G (i) Together with the ensemble learning model E, they form an ensemble network based on modular autoencoders.

[0059] It should be noted that, The subscript "m" in the middle The subscript "m" in the matrix, although representing the dimension of the feature map and the row number of the matrix respectively, is used because the feature map and the matrix correspond. The subscript "m" in the middle The subscript "m" in the original text corresponds to the same subscript. In this invention, to illustrate the correspondence between the two, the same letter "m" is used. Similarly, The subscript "n" in the text is related to... The subscript "n" in the matrix, although representing the dimension of the feature map and the column number of the matrix respectively, is used because the feature map and the matrix correspond. The subscript "n" in the text is related to... The subscript "n" in the text is corresponding. In order to illustrate the correspondence between the two, the same letter "n" is used to represent them in this invention.

[0060] In a preferred embodiment of the present invention, step S101 may include a translation transformation or a translation-rotation transformation, thereby obtaining the source data pair image I and image I′.

[0061] In the above training method, the training process of the modular autoencoder can be as follows: Figure 2 As shown, the training process of an ensemble network based on modular autoencoders can be as follows: Figure 3 As shown.

[0062] In practical applications, this invention can be implemented according to the following steps:

[0063] Step 1: Construct an autoencoder consisting of convolutions. Divide the convolution kernels into k modules. During training, input both the untransformed image I and the transformed image I′ into the constructed autoencoder, and perform convolution operations on each of the k modules to obtain the feature image for each module. Additionally, construct equivariant constraints and use these constraints to train and optimize the convolution kernel W and prediction matrix M of the constructed convolutional network autoencoder. After training, all parameters are fixed, resulting in a functionally differentiated modular autoencoder.

[0064] Step 2: Obtain the modular autoencoder with k modules trained in Step 1, with convolutional kernels W = [W (0) W (1) , ..., W (k-1) ].

[0065] Step 3: Construct k base models. These base models can be downstream task networks such as classification, segmentation, or detection networks. The k base models can be represented as [G]. (0) G (1) G (k-1) ].

[0066] Step four: Input the image I from the training data into the autoencoder trained in step one to obtain the modular feature map f = I * W, where W = [W (0) W (1) , ..., W(k-1) ], f = [f (0) f (1) , ..., f (k-1) ].

[0067] Step 5: Connect the feature maps obtained from each module to a base model to obtain G. (i) (f (i) ).

[0068] Step 6, using G (i) (f (i) ) to perform ensemble learning training E([G (0) (f (0) ), G (1) (f (1) ), ..., G (k-1) (f (k -1) )]), where E is the ensemble learning model.

[0069] Step 7: Perform supervised training, such as stochastic gradient descent, according to steps 2 through 6 to obtain the final trained base model [G]. (0) G (1) , ..., G (k-1) ] and the ensemble network model E. The trained modular autoencoder W = [W (0) W (1) , ..., W (k-1) ], base model [G (0) G (1) , ..., G (k-1) Together with the ensemble learning model E, they form an ensemble network based on modular autoencoders.

[0070] In this invention, equivariant constraints are used to enhance the correlation within modules and the independence between modules, thereby enabling modules to spontaneously differentiate their functions. For example... Figure 4 This demonstrates the effect of functional differentiation under modular and equivariant constraints. Figure 4In Figures a, b, and c, each row represents a module, and each square visualizes a learned convolutional kernel. The figures show clear functional differentiation between modules, such as differentiation in spatial frequencies, brightness, and color. Figure d visualizes the reconstruction of features extracted from each module in Figure c, providing a more intuitive view of the functional differentiation between modules in terms of color, brightness, and edges at different spatial frequencies. This modular feature differentiation is beneficial for providing a better representation space for downstream tasks, such as classification, detection, and associative generation. It also improves the robustness and generalization of downstream tasks. For example, when the style of the input image for a recognition task changes significantly, conventional classification networks may fail to recognize the image, exhibiting poor generalization. However, with the modular representation in this invention, even if the image style changes, it only affects the representation of a few modules, while having little impact on others. Therefore, through ensemble learning, it can still achieve good recognition, thereby improving the network's generalization ability.

[0071] Example 2

[0072] like Figure 5 As shown, another aspect of the present invention also includes a functional module architecture that is completely consistent with the aforementioned method flow. That is, the embodiments of the present invention also provide a training device for an integrated network based on a modular autoencoder, including:

[0073] The training data acquisition module 501 is used to acquire training data, which includes image I and image I′ obtained by transforming image I.

[0074] The autoencoder training module 502 is used to train the convolutional network autoencoder based on the training data using equivariant constraints, thereby obtaining a trained autoencoder; wherein, the equivariant constraint L EC The following formula is used for calculation:

[0075]

[0076] L equ =∑ i ||f′ (i) -M (i) (δ)f (i) || 2 , i∈{0,1,...,k-1},

[0077]

[0078] L EC =L recon +λ1L equ +λ2L sym ,

[0079] f = I * W,

[0080] f′=I′*W,

[0081] Where, I′=L δ (I), where Lδ is a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) f′ (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i) (δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC The constraint is equivariant; λ1 and λ2 are the weighting coefficients for equivariant and symmetric losses, respectively; l represents the number of dimensions for each module. This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. (i) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′ (i) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms;

[0082] The base model and ensemble learning model training module 503 is used to input the image I from the training data into the trained autoencoder to obtain the feature maps f of each module. (i) , i = 0, 1, 2, ..., k-1; for each feature map f obtained (i) Access a base model G (i) In the middle, the output result G is obtained. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and ensemble learning model E;

[0083] The modular autoencoder-based ensemble network component module 504 is used to integrate the trained autoencoder and base model G. (i) Together with the ensemble learning model E, they form an ensemble network based on modular autoencoders.

[0084] The device can be implemented using the training method of the modular autoencoder-based integrated network provided in Embodiment 1 above. For the specific implementation method, please refer to the description in Embodiment 1, which will not be repeated here.

[0085] The present invention also provides a memory that stores multiple instructions for implementing the training method of the integrated network based on modular autoencoder as described in Embodiment 1.

[0086] The present invention also provides an electronic device, including a processor and a memory connected to the processor, the memory storing a plurality of instructions which can be loaded and executed by the processor to enable the processor to perform a training method for an integrated network based on a modular autoencoder as described in Embodiment 1.

[0087] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if these modifications and modifications of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include these modifications and modifications.

Claims

1. A training method for ensemble networks based on modular autoencoders, characterized in that, include: Acquire training data, which includes image I and image I′ obtained by transforming image I; Based on the training data, the convolutional network autoencoder is trained using equivariant constraints to obtain a trained autoencoder; wherein, the equivariant constraint L... EC The following formula is used for calculation: L equ =∑ i ||f′ (i) -M (i) (δ)f (i) || 2 ,i∈{0,1,...,k-1}, L EC =L recon +λ1L equ +λ2L sym , f = I * W, f′=I′*W, Where, I′=L δ (I), L δ Let W be a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) f′ (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i) (δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC For equivariant constraints; λ1 and λ2 are the weighting coefficients of equivariant loss and symmetric loss, respectively; l represents the number of dimensions of each module; This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. (i) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′ (i) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms; The image I from the training data is input into the trained autoencoder to obtain the feature maps f of each module. (i) , i = 0, 1, 2, ..., k-1; for each feature map f obtained (i) Access a base model G (i) In the middle, the output result G is obtained. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and the trained ensemble learning model E; The trained autoencoder and the trained base model G (i) Together with the trained ensemble learning model E, they form an ensemble network based on modular autoencoders.

2. The training method for ensemble networks based on modular autoencoders as described in claim 1, characterized in that, The transformation includes translation transformation or translation-rotation transformation.

3. An integrated network based on modular autoencoders, characterized in that, It is trained using the method described in any one of claims 1-2.

4. A training device for an ensemble network based on modular autoencoders, characterized in that, include: The training data acquisition module is used to acquire training data, which includes image I and image I′ obtained by transforming image I; The autoencoder training module is used to train the convolutional network autoencoder based on the training data using equivariant constraints, thereby obtaining a trained autoencoder; wherein, the equivariant constraint L... EC The following formula is used for calculation: L equ =∑ i ||f′ (i) -M (i) (δ)f (i) || 2 ,i∈{0,1,...,k-1}, L EC =L recon +λ1L equ +λ2L sym , f = I * W, f′=I′*W, Where, I′=L δ (I), L δ Let W be a certain transformation with transformation parameter δ; W is the convolution kernel of the autoencoder of the convolutional network, and W = [W (0) W (1) , ..., W (k-1) ], that is, the convolution kernel is divided into k modules; f is the feature image obtained after convolving image I, and f = [f (0) f (1) , ..., f (k-1) f′ is the feature image obtained after convolving image I′, f′=[f′ (0) ,f' (1) ,...,f′ (k-1) ]; * indicates a convolution operation. Indicates the deconvolution operation; f (i) f′ is the feature map obtained after convolving image I through the i-th module of the convolution kernel; (i) M is the feature map obtained after convolving image I′ through the i-th module of the convolution kernel; (i) (δ) is the prediction matrix of the i-th module with parameter δ, which is obtained by random initialization and optimization through model training; L recon To rebuild the losses, L equ For equal loss, L sym For symmetrical loss, L EC The constraint is equivariant; λ1 and λ2 are the weight coefficients of the equivariant loss and symmetric loss, respectively; l represents the number of dimensions of each module. This represents the feature map of the i-th module where only the m-th dimension is 1 and the other dimensions are 0. This represents the feature map of the i-th module where only the n-th dimension is 1 and the other dimensions are 0. From arrive The optimal transformation parameters; Let the parameter be the prediction matrix M. ( i ) The value of (δ) in the m-th row and n-th column; The prediction matrix M with parameter δ′ ( i ) The value of (δ′) in the m-th row and n-th column; T is a hyperparameter greater than 0; For the transformation parameters are The prediction matrix at time; δ′ is the integration variable, used to distinguish the transformation parameter δ under different integration terms; The base model and ensemble learning model training module is used to input the image I from the training data into the trained autoencoder to obtain the feature maps f of each module. (i) Let i = 0, 1, 2, ..., k-1; then, input each feature map f(i) into a base model G(i) to obtain the output G. (i) (f (i) ); using the output results G of each base model (i) (f (i) The ensemble learning model E is trained to obtain the trained base model G. (i) and the trained ensemble learning model E; The modular autoencoder-based ensemble network is used to construct modules for training the autoencoder and the trained base model G. (i) Together with the trained ensemble learning model E, they form an ensemble network based on modular autoencoders.

5. The training device for an integrated network based on modular autoencoders as described in claim 4, characterized in that, The transformation includes translation transformation or translation-rotation transformation.

6. A memory, characterized in that, The system stores multiple instructions for implementing the training method of the ensemble network based on modular autoencoders as described in any one of claims 1-2.

7. An electronic device, characterized in that, The system includes a processor and a memory connected to the processor, the memory storing multiple instructions that can be loaded and executed by the processor to enable the processor to perform the training method for an integrated network based on a modular autoencoder as described in any one of claims 1-2.

Images