17 results about "Class separability" patented technology

The invention discloses a prompt-driven two-stage multi-modal emotion representation learning method. The method comprises the following steps: respectively collecting original video data from a plurality of public multi-modal emotion analysis data sets; preprocessing and feature extraction are carried out to obtain vectorized multi-modal feature representations of vision, audio and texts, and multi-source emotion clues are obtained; in a training stage, a prompt-driven two-stage multi-modal emotion representation learning model is constructed, inter-class separability is enhanced and intra-class intensity features are reserved through an emotion anchor point comparison and alignment stage, including prompt-based emotion anchor point learning and comparison and alignment between joint representation and emotion anchor points; capturing the dynamic change of emotion expression through an emotion intensity offset estimation stage; in the reasoning stage, emotion category prediction and final emotion state prediction are carried out. According to the method, shared emotion features among multiple modes can be stably captured, interference caused by individual differences is effectively suppressed, and the accuracy and robustness of emotion prediction are remarkably improved.

The application discloses an iris recognition method and device, system and storage medium, and performs preprocessing such as polar coordinate unfolding on an input original iris image in sequence; multi-level image features are extracted through an inverse residual module; subsequently, a global depth convolution GDConv operator is introduced to replace a global average pooling layer, so that spatial structure distribution features of iris textures are retained under the premise of extremely low calculation complexity; finally, an ArcFace loss function is used to optimize the distribution of features in a hyperspherical space, and the class separability of the features is enhanced by introducing an additive angle interval. By using the technical scheme of the application, the technical problems that spatial topological information is lost due to a global average pooling GAP operation in iris feature extraction by using an existing lightweight convolutional neural network, and the feature discrimination is reduced due to network lightweight are solved.

The application discloses a kind of key equipment intelligent diagnosis method and system for rotating machinery, it is related to the technical field of fault diagnosis and prediction, including, with physical inspiration as guidance, in feature learning stage, introduce bounded metric encapsulation mechanism, traditional unbounded feature space is mapped into bounded similarity manifold, to suppress high-dimensional space distance concentration effect and improve inter-class separability and intra-class compactness.In bounded metric space, realize multi-fault identification by combining near neighbor or support vector classifier.The application has significant improvement in weak fault (germination period) detection, composite / multiclass fault distinction and robustness under low signal-to-noise ratio condition, has good explainability and engineering deployment value, is suitable for the predictive maintenance and online health monitoring of wind power, rail transit, aerospace and process manufacturing and other scenes.

This invention belongs to the interdisciplinary field of medical image analysis and deep learning, and discloses a method and apparatus for pathological slide image segmentation using multimodal supervised contrastive learning. The method generates biological prior feature maps through decoupling, extracts visual and semantic features by combining the master encoder and prior encoder, and achieves feature alignment using a cross-modal attention mechanism. Supervised contrastive learning is introduced to enhance intra-class compactness and inter-class separability. A multi-scale decoupled decoder is designed, with structural similarity loss and boundary-aware loss respectively supervising structural and detail branches. Finally, dynamic weighted fusion and pseudo-label calibration strategies are used to optimize segmentation performance, significantly improving the accuracy and robustness of pathological image segmentation.

This invention discloses an open-set specific radiation source identification method and system based on multi-granularity embedding guidance. First, selective attention complex convolution branches and Transformer branches are used to extract local fine-grained features and global temporal dependency features of radio frequency signals, respectively. Then, an attention-guided multi-scale feature fusion module performs cross-granularity alignment and semantic fusion on the dual-path features. A label-aware discriminative prototype embedding space is constructed, and joint loss is used to optimize the embedding space to enhance intra-class aggregation and inter-class separability. Unidentified unknown class samples are projected into the discriminative embedding space, and an angle-based prototype incremental update mechanism is used to further identify and subdivide the unknown categories. This invention can simultaneously achieve high-precision identification of known radiation sources and detection and subdivision of unknown radiation sources in open-set scenarios, significantly improving generalization ability and identification stability in complex real-world environments.

A semi-supervised medical image segmentation method based on diffusion-driven hard-soft prototype comparative learning belongs to the field of medical image processing and comprises the following steps: acquiring a medical image and dividing the medical image into a labeled data set and a non-labeled data set; generating a pixel-level confidence map by using a discriminator; using a confidence map to guide a diffusion model to carry out adaptive denoising and correction on the noise pseudo label, and introducing a local detail enhancement mechanism to generate a corrected pseudo label; a hard-soft collaborative prototype comparison module is constructed, a category prototype is constructed based on the corrected pseudo tag, a hard matching indication matrix is generated for high-confidence pixels, soft guidance constraint is applied to low-confidence pixels, and intra-class compactness and inter-class separability of a feature space are enhanced; performing iterative optimization on the model through a joint optimization objective function; inputting the medical image to be segmented into the trained segmentation network to obtain a segmentation result; according to the method, the problems of pseudo label noise accumulation and feature discrimination degradation in semi-supervised learning are solved, and the dependence on large-scale labeled data is reduced.

The invention belongs to the technical field of image recognition, and particularly relates to a CT image motion artifact classification model construction method and system based on feature prototype contrast learning. According to the classification method based on the prototype, the class center is used as feature storage, the inter-class separability and the intra-class consistency in the artifact classification task are enhanced, and the robustness and the classification precision of the model are remarkably improved. The method specifically adopts a Vision Transform (ViT) as a basic model for feature extraction, combines a strong global modeling capability, effectively captures long-range dependence and fine-grained features in artifact detection, and improves the capability of identifying the complexity of artifact types. And by introducing a prototype contrast learning strategy, the feature representation of the artifact image is optimized, and the overfitting problem of the model when training data is insufficient is relieved, so that the generalization ability and robustness of the model in practical application are improved, and an excellent classification result is obtained on a clinical data set.

The present application belongs to the technical field of computer, and particularly to a face forgery detection system based on uncertain modeling.The system comprises a probabilistic Transformer module, an image block screening module and an uncertainty-aware single classification loss function module.The present application firstly models the dependency relationship between image blocks as Gaussian random variables, extends the Transformer model in a probabilistic manner, then introduces an image block selection module to identify areas with high uncertainty information for final classification, and finally quantifies the uncertainty of the entire image, uses the designed uncertainty-aware single classification loss function to make the model focus more on samples with high uncertainty and difficult to determine, and through only enhancing the internal compactness of real faces, improves the inter-class separability of real and false classes in the embedding space.

The invention discloses an open set specific radiation source identification method and system based on multi-granularity embedding guidance. The method comprises the following steps: firstly, respectively extracting local fine granularity features and global time sequence dependence features of radio frequency signals by using a selective attention complex convolution branch and a Transform branch; carrying out cross-granularity alignment and semantic fusion on the dual-path features through an attention-guided multi-scale feature fusion module; constructing a label perception discrimination prototype embedding space, and optimizing the embedding space by using joint loss to enhance intra-class aggregation and inter-class separability; and projecting the rejected unknown class sample to a discriminative embedding space, and realizing further identification and subdivision of the unknown class by using an angle-based prototype increment updating mechanism. According to the invention, in an open set scene, high-precision identification of a known radiation source and detection and subdivision of an unknown radiation source can be realized at the same time, and generalization ability and identification stability in a complex real environment are significantly improved.

The present application relates to the technical field of remote sensing change detection, and discloses a remote sensing change detection method and system based on change decoupling enhancement, comprising: acquiring double-time-phase remote sensing images, constructing a change decoupling enhancement network model, the model comprising a double-branch encoder, a change representation decoupling module, a semantic consistency enhancement module and a segmentation head, the double-branch encoder extracts double-time-phase features of a double-time-phase image pair at different scales, the change representation decoupling module explicitly identifies and separates unchanged components by calculating the similarity between the double-time-phase features, the semantic consistency enhancement module enhances intra-class consistency and inter-class separability by dividing the change representation into multiple semantic groups and independently refining them, and the segmentation head performs remote sensing change detection according to semantic features. The present application can improve the semantic discrimination ability of change detection, thereby improving the accuracy of remote sensing change detection.

The application provides a gas transient signal rapid detection method based on Mamba and ordinal metric learning, and relates to the technical field of gas detection and analysis. In view of the problems that the existing gas sensor relies on steady-state signals, resulting in long detection time, insufficient utilization of transient signals, and high intra-class variance and poor inter-class separability of transient signals, the application proposes a MOML framework based on Mamba encoder and triplet loss metric learning. The framework uses the Mamba encoder to extract long sequence features from the transient dynamic response signals of the gas sensor and map them to the embedding space; the embedding space is optimized through the triplet loss to enhance the intra-class compactness and inter-class separability; especially for the gas concentration regression task, a neighborhood negative sampling strategy is designed to realize ordinal metric learning. The experimental results show that the application can significantly improve the feature separability, improve the gas type recognition accuracy and concentration prediction accuracy, and realize low-delay and high-precision gas detection.

The invention discloses a hyperspectral image ensemble classification method combined with TRP matrixes of different dimensions. A fitness function is designed by adopting a genetic algorithm and considering category separability and low-dimensional correlation at the same time, TRP matrixes of different dimensions are optimized, an optimal TRP matrix set is obtained, and adaptive selection of projection dimensions is realized; secondly, projecting the hyperspectral image to a corresponding low-dimensional space by using the optimized TRP matrixes with different dimensions, and classifying each piece of low-dimensional data by using a support vector machine; fusing the plurality of classification results by adopting a majority voting strategy to obtain a more accurate and stable final classification result; in order to verify the effectiveness of the method, experiments are carried out on real images, and results show that the method is excellent in calculation efficiency and classification precision.

The invention discloses a knowledge enhancement recommendation method based on a large language model and multi-view comparative learning, relates to a data mining and graph topological structure analysis technology, and provides a scheme for solving the problems that an existing method in the prior art is insufficient in representation discrimination, an embedded space is prone to collapse and the like. The method comprises the following steps: preprocessing data, constructing a user-article bigraph, carrying out semantic embedding based on a large language model, constructing multiple views after learning graph neural network collaborative representation, carrying out comparative learning on the multiple views, optimizing the model, calculating total loss, and generating recommendation and outputting the recommendation. The method has the advantages that the representation capability of a recommendation system is remarkably enhanced, the problems of excessive smoothness and sensitivity to noise in the graph convolution process are relieved, discrimination signals in contrast learning are enhanced, good inter-class separability is kept, and recommendation sorting performance is centrally optimized.

The application discloses a kind of semi-supervised industrial surface defect segmentation method, system and storage medium, belong to defect segmentation field, including: training phase and application phase.In training phase, direction consistency regularization based on confidence guide is used instead of average consistency regularization, and the quality of feature alignment is improved;At the same time, the confidence perception hybrid pseudo-label method generation method is designed, and the influence of confirmation bias of unlabeled data is reduced;And, the foreground-background contrast learning strategy is introduced to improve the class separability of feature space, encourage normal area or defect area to have similar representation in feature space, while the features between normal area and defect area are far away from each other, guide the model to identify defect features more accurately;In the case of limited data labels, additional supervision signals can be extracted from a large amount of unlabeled data, the training process of the model is completed, and the prediction accuracy of the model is effectively improved.

The invention provides a gas transient signal rapid detection method based on Mama and ordinal number metric learning, and relates to the technical field of gas detection and analysis. Aiming at the problems of long detection time, insufficient utilization of transient signals, high intra-class variance and poor inter-class separability of the transient signals caused by dependence on steady-state signals of an existing gas sensor, the invention provides an MOML framework based on a Mama encoder and triple loss metric learning. The framework utilizes a Mama encoder to extract long sequence features from transient dynamic response signals of a gas sensor and map the long sequence features to an embedding space; the embedding space is optimized through triple loss, and intra-class compactness and inter-class separability are enhanced; especially for a gas concentration regression task, a neighborhood negative sampling strategy is designed to realize ordinal number metric learning. Experimental results show that the characteristic separability can be remarkably improved, the gas type recognition precision and the concentration prediction accuracy are improved, and low-delay and high-precision gas detection is achieved.

The application discloses a kind of enhanced field adaptation's vibrating screen cross-domain fault diagnosis method, comprising: the different field vibrating screen multidimensional comprehensive fault data set obtained is divided into source domain feature training set, target domain feature training set and target domain feature test set;Source domain feature training set and target domain feature training set are mapped to random feature space and are processed to joint distribution difference, to execute the field and class alignment of feature;Source domain feature training set is processed to field feature discrimination, to enhance the intra-class tightness and inter-class separability of feature;According to the joint distribution difference processing result and the field feature discrimination processing result, based on the enhanced field adaptation incremental random vector function chain network, a vibrating screen cross-domain fault diagnosis model is constructed, which is used to predict the fault class of unknown label in target domain. The application effectively overcomes the challenge of domain shift, and also significantly improves the performance and generalization ability of the vibrating screen fault diagnosis model.

The invention relates to the technical field of load feature extraction, and discloses a load feature self-extraction method, system, equipment and medium based on supervised metric learning, and the method comprises the steps: obtaining original current and voltage signals of a target electric appliance, and generating a multi-dimensional initial power fingerprint feature set through time-frequency domain transformation; inputting the feature set into a pre-trained mask auto-encoder, generating a low-dimensional potential feature vector through the encoder, and constructing an intra-class compactness and inter-class separation constraint and joint optimization model by using a supervised metric learning strategy in combination with an electric appliance class label; and finally, outputting a strong-universality load feature vector for non-intrusive load identification. According to the method, self-supervised reconstruction and supervised metric learning are fused, the feature discrimination and generalization ability are effectively improved, dependence on a large amount of labeled data is reduced, and the method is suitable for high-precision equipment identification under complex aliasing signals.