43 results about "Similarity learning" patented technology

The invention discloses a test question management method based on multi-modal adaptive similarity learning, and relates to the technical field of data management, and the method comprises the steps: collecting an original test question set, generating an evolutionary test question set through a preset large language model, generating a variable test question set through a data enhancement technology, and carrying out the fusion processing of the test question set to form a test question ecological library, the diversity and coverage of test question resources are enriched; the test question ecological library is input into a preset semantic similarity model and a preset syntactic similarity model to obtain a semantic similarity score and a syntactic similarity score of each test question, so that the similarity of the test questions can be comprehensively measured, and the screening accuracy is improved; the multi-modal similarity score is obtained according to the semantic similarity score and the syntactic similarity score to be compared with the preset threshold value, then the test questions are imported into the auditing module or the question bank storage module according to the comparison result, intelligent distribution of the test questions is facilitated, and the timeliness and quality of the question bank are ensured.

The invention relates to the field of off-post personnel identification, in particular to an off-post personnel identification system and method. The method is characterized in that a target detection module is constructed based on the OfficientViT, by means of the OfficientViT target detection module, by means of a linear attention mechanism and a multi-scale feature fusion technology, the high detection precision of 91.8% is maintained, efficient calculation processing is achieved, and in the trajectory tracking layer, by means of a quasi-dense similarity learning algorithm based on QDTrack and a cascade matching strategy, the detection precision of the target detection module is greatly improved. According to the method, the tracking capability of the system on a shielded target and a long-time disappearing target is greatly improved, in the behavior decision-making level, the space-time fusion decision-making module constructs an accurate departure behavior judgment mechanism by means of fusion time logic and space logic, and the overall departure recognition accuracy of the system is improved to 93.2%. A comprehensive experiment result shows that the system has excellent performance in various supervision scenes, and has relatively large performance advantages and practical value when being used for processing departure behavior identification in a complex environment.

The invention provides a foreign matter intelligent identification and dynamic monitoring method based on remote sensing data fusion, and belongs to the field of image identification. The problem of low foreign matter recognition efficiency is solved; the method specifically comprises the following steps: acquiring and extracting fusion features of remote sensing pictures of various road foreign matters; similarity learning is carried out on the fusion features, and a high-dimensional index structure is established; acquiring a real-time remote sensing picture on the road, and judging whether foreign matters exist on the road or not; if so, marking a foreign matter; if not, not processing; acquiring a historical natural image of a target area, designing a time sequence feature analysis module, a spatial feature analysis module and a spatio-temporal joint prediction module, and outputting a natural environment prediction image of the target area at a future moment; acquiring an actual remote sensing image, and marking an abnormal region in the actual remote sensing image according to the natural environment prediction image; according to the method, the foreign matter recognition efficiency is improved through obtaining and feature extraction of the remote sensing images in the road and natural environment of the target area.

The invention discloses a three-level interactive fusion graph similarity learning method, which comprises the following steps: learning node embedding through a multi-layer GIN in jump connection, and designing a style-based multi-head attention mechanism to capture fine-grained node-node interaction information; a coarse and fine granularity aggregation network is combined with different attention mechanisms to generate graph embedding features of two granularities, and the graph embedding features are fused; generating new node embedding through fusing cross-node-graph interaction information by adopting a node-graph interaction comparison network, and finally learning comparison characteristics of original node embedding and new node embedding; and performing global-level graph-graph interaction modeling on a relationship between input graphs by fusing comparison features and aggregation features generated by a graph interaction learning module and utilizing a full connection layer based on multi-level features of two input graphs, and converting the relationship into a graph-graph similarity score. Learning of enhanced node embedding is focused on, and rich graph interaction features are generated through a more effective graph interaction learning mode so as to promote modeling of a graph similarity relationship.

A method for locating at least one anomaly in a spatio-temporal piece of data includes obtaining a spatio-temporal piece of data, obtaining a neural network configured to generate a piece of information of locating at least one anomaly from a spatio-temporal piece of data, generating, by the neural network obtained, the piece of information of locating the at least one anomaly by providing the spatio-temporal piece of data obtained to the neural network, obtaining an accuracy score provided by a user evaluating an accuracy of the generated piece of information of locating the at least one anomaly, reinforcement learning the neural network, and similarity learning the neural network reinforcement learned.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses an image similarity retrieval method, device and equipment and a medium. Inputting the data and a feature pyramid into a similarity learning module for cross-level constraint training to obtain an updated module and a trained similarity learning module; and storing the training hierarchical semantic structure to a database management module, processing the query image by using the updated module to generate a query hierarchical semantic structure, performing multi-level comparison based on the trained similarity learning module to obtain a comprehensive matching result, and outputting a retrieval image set by the database management module. According to the method, unified modeling and alignment of multi-scale semantic features are realized through cross-level constraint training and multi-level comparison, and the retrieval accuracy and efficiency are improved.

An initial noisy graph topology is obtained and an initial adjacency matrix is generated by a similarity learning component using similarity learning and a similarity metric function. An updated adjacency matrix with node embeddings is produced from the initial adjacency matrix using a graph neural network (GNN). The node embeddings are fed back to revise the similarity learning component. The generating, producing, and feeding back operations are repeated for a plurality of iterations.

Aspects presented herein may enhance the accuracy and / or latency of UE positioning based on crowd-sourcing, where a network entity may compute a position estimate of a UE based on neighbor-cell scan data from the UE and one or more reference UEs. In one aspect, a network entity receives a first set of measurements associated with at least one cell from a UE. The network entity performs a position estimation of the UE based on at least one of the first set of measurements associated with the at least one cell, a second set of measurements for each of a set of reference UEs, or a location of each of the set of reference UEs via an ML model, where the UE and the set of reference UEs include at least one common cell.

This invention discloses a remote sensing image crop classification method based on self-supervised learning. This method extracts rule-compliant crop sample data through a fully automated sample selection method. This crop sample data is processed into a coarse training sample set. Representation learning is performed using proxy tasks combined with an attention mechanism. Similar images of each remote sensing image are determined based on feature similarity. The proxy features are then used as prior conditions for semantic clustering, and refined classification is performed using the maximized dot product after softmax as the loss function. This method performs unsupervised training on the image's own feature similarity learning method, completing crop classification through clustering, avoiding the tedious and expensive process of manually annotating data. Compared with traditional manual feature extraction methods, this method is more adaptable to the complexity and variability of remote sensing images and can better utilize unlabeled data for training, improving the accuracy of crop classification.

The invention discloses a multi-modal false news detection method based on an attention mechanism. The method comprises the steps that firstly, an interaction control vector is created, and an attention weight vector is calculated; then, obtaining the similarity among the multi-modal data by using the initial feature vectors; and finally, combining the attention weight vector and the feature vector of the similarity learning news content, and selecting a corresponding deep learning model to detect the authenticity of the news according to the obtained feature vector. The accuracy and credibility of the false news detection result are improved, the false news detection efficiency is improved, and the false news detection cost is reduced.

The invention discloses an audiovisual event identification and positioning method, system and device based on semantic consistency fragment selection and a medium. The method comprises the following steps: constructing an audiovisual event identification and positioning model based on semantic consistency fragment selection; designing a loss function, continuously training and optimizing the audiovisual event recognition and positioning model based on semantic consistent fragment selection through the loss function, and when the loss function is minimum, obtaining an optimal audiovisual event recognition and positioning model based on semantic consistent fragment selection; inputting the target video into the optimal audio-visual event recognition and positioning model based on semantic consistent fragment selection to obtain optimal target event recognition accuracy and positioning information of the target event; the system, the equipment and the medium are used for implementing the method. The invention provides a multi-modal similarity learning model and a global semantic perception and enhancement module to solve the problem of semantic imbalance between audio and video clips and improve the semantic consistency of audio-visual modalities.

The embodiment of the invention discloses a face detection method and device, computer equipment and a storage medium. According to the scheme, the plurality of anchoring samples are determined according to the AU label combination category of the face image in the data set, the samples with the same AU information as the anchoring samples are used as the positive samples, the samples with different AU information from the anchoring samples are used as the negative samples, and the triple samples are constructed based on the anchoring samples, the positive samples and the negative samples, so that the face recognition accuracy is improved. Inputting the triple sample into a global facial expression feature extraction module for feature extraction to obtain a feature vector corresponding to each sample image, and further, respectively sending the feature vectors into a similarity module and a detection module for respectively learning AU combination similarity information and AU category information in the input triple sample, the AU detection and the AU combination similarity learning are organically combined, and the AU combination similarity learning task is utilized to assist the AU detection task, so that the AU detection effect in the face image can be improved.

The invention discloses an image-text cross-modal retrieval method and system based on high-dimensional ball embedding, and the method comprises the steps: carrying out the feature extraction processing of a target image and a target text through a backbone network and a word embedding method based on the target image and the target text, and obtaining a visual feature and a text feature; based on a ball encoder, performing center calculation and semantic uncertainty modeling of ball embedding to obtain a visual ball center vector, a visual uncertainty radius, a text ball center vector and a text uncertainty radius; similarity learning is carried out on the center vector and radius of the ball through a Monte Carlo sampling method of ball embedding, and image text cross-modal retrieval is achieved. According to the method, cross-modal alignment is enhanced through semantic uncertainty and diversity between visual texts, so that the cross-modal retrieval precision of the image texts is improved. The image-text cross-modal retrieval method and system based on high-dimensional ball embedding can be widely applied to the technical field of image-text retrieval.

The invention relates to a cross-scene small sample animal key point detection method based on deformable Mama, and belongs to the field of computer vision. According to the method, existing basic key points and new key points can be positioned in new species through a small number of reference samples. According to the invention, a comparative learning and similarity learning mechanism between key points is introduced to improve the positioning capability of a cross-scene small sample key point detector for any key point. Meanwhile, a deformable Vision Mama encoder module is adopted, and the module can effectively capture a long-distance relationship, performs optimization processing for different inputs, and can better adapt to the shape of an animal in key point detection, so that the key points and the mutual relationship between the key points are more accurately positioned. In addition, a saliency map is introduced to help a cross-scene small sample key point detection network to focus on a foreground region better, so that the detection effect and robustness are further improved. And finally, animal key points in indoor and outdoor scenes can be detected.

The present invention relates to the field of image target recognition technology, and more specifically to a zero-shot SAR image target recognition method based on joint distribution adaptation. The training phase of the method does not require the participation of measured data for the task of interest. Instead, the method utilizes simulated SAR images and utilizes multi-kernel maximum mean difference to minimize the distance between the dual-domain mappings of the simulated and measured domains. This encourages similarity between the two sets of representations, learns domain-invariant features, and effectively mitigates domain differences. By capturing category information, the method automatically achieves fine-grained sub-domain adaptation, automatically and efficiently improving the robustness and recognition rate of the model.

The invention discloses a multi-view agricultural image clustering method based on enhanced multi-order similarity learning, and relates to the technical field of image clustering, and the method comprises the following steps: preprocessing image data, constructing an initial affinity matrix which is used for representing the affinity between data points, the method comprises the following steps: capturing a local structure and a neighborhood relationship of data points through first-order similarity and second-order similarity, stacking and rotating all affinity matrixes into a third-order tensor, constraining by using a weighted tensor Schatten-p norm, and optimizing all modules in a unified optimization framework. According to the method, through parallel mining of multi-order similarity, weighted tensor Schatten-p norm optimization and unified spectral clustering fusion, multi-view data complementary features are fully utilized, clustering precision and robustness are improved, and reliable technical support can be provided for precise agricultural application such as crop health monitoring and pest and disease damage detection.

The invention relates to a radar scene sensing method, device and equipment based on RADRadar. The method comprises the following steps: constructing an RADRadar model; the RADRadar model comprises a feature similarity learning module and an outer product module; calculating a channel similarity matrix of every two of the RA view, the RD view and the AD view along a feature channel dimension by using a feature similarity learning module, and updating one of the two low-dimensional views subjected to outer product according to the channel similarity matrix to obtain an updated low-dimensional view; and reconstructing the updated low-dimensional view and another original low-dimensional view according to the outer product module to obtain a reconstructed RAD feature cube. By adopting the method, coupling learning among multiple dimensions can be realized.

The application discloses an industrial control abnormality detection method based on high-low frequency feature similarity, which firstly carries out periodic collection of monitoring data from an industrial control system field, and constructs corresponding low-frequency feature vectors and high-frequency feature sets. Through repeated data collection, a training data set containing multiple samples is formed. In the initialization process of the abnormality detection network, a combination of a feature transformation network and a projection network is adopted to ensure effective mapping and fusion of the low-frequency features and the high-frequency features. Specifically, the low-frequency feature vectors are mapped to a unified dimension through a linear transformation matrix, and the high-frequency features are directly input into an attention fusion mechanism to calculate the dynamic correlation degree of the high-frequency features to the low-frequency features. Finally, the projection network is used to map the fused features and the low-frequency features to generate a vector pair for similarity learning. The application can solve the technical problems of the deficiencies of the conventional industrial control system abnormality detection method in feature processing and fusion.

The invention provides an equipment energy consumption state monitoring method based on electric signals of a multi-energy complementary energy supply system, and the method comprises the steps: obtaining time sequence electric signals of all energy consumption equipment, carrying out the preprocessing, extracting multi-dimensional features, constructing feature vectors, and carrying out the collection to obtain an original sample set; disturbance enhancement is applied to the original sample in the known state, and an abnormal behavior agent sample set is generated; the method comprises the following steps: constructing an Encoder-Classifier architecture model on the basis of a two-stage model training mechanism; acquiring electric signals in real time, outputting the electric signals according to a fixed window, preprocessing and extracting features, and inputting the features into the model to obtain monitoring results. According to the method, the electric signal time sequence characteristic and the equipment operation rule are combined, the abnormal behavior agent sample can be automatically generated without an abnormal label, and a complex equipment scene is adapted; through double-stage training of data enhancement and similarity learning, the model recognizes the state and abnormity of equipment, and intelligent support is provided for safe operation and energy efficiency improvement of a multi-energy system.

Methods and systems for attributing browsing activity from two or more different network-connected devices to a single user are disclosed. In one aspect, cookies generated by the browsing activity of different unidentified devices at a website are received. A random forest classifier trained on probabilities output from a Gaussian mixture model is applied to the unidentified cookies to determine a probability that two different cookies were generated by the same user. In some embodiments, personalized content is then delivered to the user based on the characteristics of the paired cookies.

Systems and methods for preference and similarity learning arc disclosed. The systems and methods improve efficiency for both searching datasets and embedding objects within the datasets. The systems and methods for preference embedding include identifying paired comparisons closest to a user's true preference point. The processes include removing obvious paired comparisons and / or ambiguous paired comparisons from subsequent queries The systems and methods for similarity learning include providing larger rank orderings of tuples to increase the context of the information in a dataset In each embodiment, the systems and methods can embed user responses in a Euclidean space such that distances between objects are indicative of user preference or similarity.

The present invention belongs to the fields of deep learning and brain network structure, and particularly relates to a joint learning method for brain network structure and similarity based on graph attention network, including: performing cortical segmentation processing and morphological feature extraction on the obtained brain image data, and modeling the subject's brain network as a graph; estimating the initial brain network structure through Pearson correlation calculation; obtaining the similarity between brain network structures through a siamese graph attention learning network; calculating the graph regularization loss function and the siamese network loss function to constrain the characteristics of the initial brain network structure; updating the adjacency matrix of the brain network according to the embedding features of the brain network, and obtaining the updated brain network structure and calculating the similarity of the brain network structure. The present invention effectively estimates the morphological brain network by jointly optimizing the two tasks of brain network structure estimation and similarity learning, and provides valuable information for subsequent tasks such as individual recognition and disease auxiliary diagnosis.

The application provides a kind of based on the energy state monitoring method of equipment of multi-energy complementary energy supply system electric signal, steps include: obtaining each energy equipment timing electric signal, extracts multi-dimensional feature after pre-processing and constructs feature vector, and obtains original sample set in set;Known state original sample is applied to enhance, and abnormal behavior agent sample set is generated;Based on the two-stage model training mechanism, the Encoder-Classifier architecture model is constructed;Real-time acquisition of electric signal and output according to fixed window, pre-treatment is extracted into the model after feature and the monitoring result is obtained.The application combines the timing characteristics of electric signal and the operation law of equipment, can automatically generate abnormal behavior agent sample and does not need abnormal label, adapts to complex equipment scene;Through two-stage training of data enhancement and similarity learning, the model identifies equipment state and abnormality, and provides intelligent support for safe operation and energy efficiency improvement of multi-energy system.

The application discloses an image similarity matching method based on attention weight distribution of external memory, comprising the following steps: 1, obtaining image original features of an image data set; 2, replacing the image original features with the result of representation learning to obtain high-level representation thereof; 3, performing simple similarity calculation on input samples to obtain external initial memory thereof; 4, constructing two external selection models to distribute external memory selection weights, including an external sample selection model and an external relationship selection model; 5, optimizing and training the external selection models by using two training methods of selection optimization and global optimization to obtain an optimal training model; and 6, detecting the input samples by using the trained external selection model to obtain an image pair with the highest external memory selection weight as the most similar image pair. The application can improve the similarity learning effect, thereby obtaining the globally most similar image, and the image matching result has better interpretability.

The application discloses a long video retrieval method and device based on multi-scale multi-example similarity learning. The method acquires video and text preliminary features; uses coarse-to-fine coding mode to extract information of different time granularities from video segment scale and frame scale; based on video representation of two scales, uses segment scale similarity learning branch to filter out video segments most relevant to the text and obtain segment scale similarity; uses frame scale similarity learning branch to aggregate video features guided by the filtered most relevant video segments to obtain more detailed video information, and after similarity calculation with the text, frame scale similarity is obtained; a common space learning algorithm is used to learn multi-scale similarity between long videos and texts, and a model is trained in an end-to-end manner to realize text-to-long video retrieval. The application uses the idea of multi-scale multi-example learning, and can effectively solve the text-to-long video retrieval task.

Systems and methods for similarity learning in digital pathology are provided. In one aspect, an apparatus for generating training image data includes a hardware memory configured to store executable instructions and a hardware processor in communication with the hardware memory, wherein the executable instructions, when executed by the processor, cause the processor to obtain a plurality of histopathology images, classify two or more of the histopathology images as similar or dissimilar, and create a dataset of training image data including the classified histopathology images.

The invention discloses an industrial control anomaly detection method based on high and low frequency feature similarity, and the method comprises the steps: carrying out the periodic collection of monitoring data from an industrial control system site, and constructing a corresponding low-frequency feature vector and a high-frequency feature set; through repeated data acquisition, a training data set containing multiple samples is formed. In the initialization process of the anomaly detection network, the combination of the feature transformation network and the projection network is adopted to ensure the effective mapping and fusion of the low-frequency features and the high-frequency features. Specifically, low-frequency feature vectors are subjected to unified-dimension mapping through a linear transformation matrix, and high-frequency features are directly input into an attention fusion mechanism so as to calculate the dynamic correlation degree of the high-frequency features to the low-frequency features. And finally, mapping the fusion feature and the low-frequency feature by using a projection network, and generating a vector pair for similarity learning. The technical problem that a traditional industrial control system anomaly detection method is insufficient in feature processing and fusion can be solved.

The present invention provides a multimodal fusion fine-tuning training method, device, electronic device and readable storage medium, the method includes obtaining a point cloud model P of a starting 3D model i and several multi-views; obtain the point cloud model P through self-supervised learning i The eigenvector Z i , and the multi-view 512-dimensional feature vector h i ; For the eigenvector Z i With the eigenvector h i Splice and get the 512-dimensional fusion feature vector f i ; Fuse feature vector f through DHC loss function i The hierarchical classification fine-tuning training is performed and the fusion feature vector f is performed through the batch center similarity learning mechanism i Metric learning fine-tuning training. The fusion of two self-supervised learning feature vectors leverages the strengths of different input technology approaches, improving the retrieval accuracy of the model's feature vectors. Fine-tuning training on a small amount of classification data allows the model to quickly learn classification information preset for specific tasks. The metric learning mechanism ensures the distance between different subcategories in the feature vector space.

The invention discloses an image-text retrieval method and system based on fine-grained alignment and reordering, and the method comprises the steps: inputting an image and a text to be retrieved, and carrying out the coding of the inputted image-text through the powerful feature extraction capability of a pre-training model CLIP; adaptively aligning the text representation to a related image region by using a cross-modal interaction module; calculating a similarity score between the image and the text to obtain a preliminary matching result; performing reverse retrieval on the initial similarity matrix through a reordering mechanism; a retrieval model is trained in combination with three loss functions, knowledge extracted offline by a single-mode pre-training teacher model is introduced as a soft label supervision signal, and a similarity learning process is optimized; the KL divergence is used to measure the difference between the probability distribution output by the model and the soft label provided by the teacher model, and the semantic alignment capability between images and texts is improved. According to the method, three loss models are used in a combined manner, so that the semantic relationship between images and texts is effectively aligned, and the clearness and consistency of the internal structure of the modal are ensured.

The present application relates to the field of trajectory recognition, and particularly relates to a kind of open environment vehicle abnormal trajectory detection model architecture method, its model includes coding network, embedding network and inference network.In training phase, first, the total loss including similarity loss and cross-entropy loss is used to update model parameters, then, the updated model is used to update similarity learning network using cross-entropy loss until training is completed.The calculation of the similarity loss includes: based on trajectory embedding, the similarity between trajectories is calculated using similarity learning network, the cross-entropy loss is calculated based on the predicted probability distribution and the similarity between trajectories, then, the similarity loss is calculated by aligning the two types of similarity.The method of the present application introduces similarity loss, so that the model not only learns the classification of a single trajectory, but also understands the relationship and connection between different trajectories, which can effectively classify unknown abnormal behavior in the environment under the assumption of open world.