11 results about "Class discrimination" patented technology

The application belongs to the technical field of open set identification, and discloses an open set identification method based on a hierarchical visual semantic attribute space. The application can not only accurately identify whether a target belongs to a seen class or an unseen class, but also can explicitly determine the coarse-grained class to which the target belongs and the specific attributes possessed by the target. Compared with the traditional open set identification technology, the open set identification method based on the hierarchical visual semantic attribute space has significant advantages, greatly improves the explainability of the model, and enables the model to not only give a simple unknown class discrimination when facing unknown targets, but also provide more valuable information, thereby providing solid technical support for the effective deployment of the model in complex real-world scenarios.

The invention discloses a high-resolution remote sensing building extraction method. The method comprises the following steps: acquiring multi-scale feature data and shallow enhancement feature data; obtaining deep enhancement feature data; obtaining fusion features; and generating a building extraction result. According to the method, a shallow feature enhancement module is constructed in a shallow spatial information representation stage, so that a network can more accurately highlight building related channels in a complex scene, redundant background information is inhibited, and the category discrimination capability and the positioning reliability are improved; according to the method, a deep feature enhancement module is constructed in a deep semantic information representation stage, the continuity and semantic integrity of a building boundary are improved, the perception and extraction capability of a small-scale building is enhanced, and false detection and missing detection are reduced; according to the method, a lightweight edge feature reconstruction decoder is designed in a decoding stage, so that boundary blur and artifacts caused by traditional interpolation up-sampling are effectively suppressed, and decoding stability and boundary recovery quality are improved on the premise of reducing parameter quantity and calculation overhead.

The invention discloses a family dangerous object identification method and system based on improved YOLOv8, and belongs to the technical field of computer vision and edge computing. Aiming at the problems of long tail distribution of dangerous objects in a family scene, missing detection of small targets, false alarm of similar objects and limited computing power of edge equipment, three improvements are carried out on a YOLOv8s model: a class prototype adaptive mechanism is introduced, and the long tail class discrimination capability is enhanced; a multi-scale feature enhancement module is added, and the small target feature extraction effect is improved; a coordinate attention mechanism is embedded, and the target positioning precision is enhanced. Furthermore, the detection result is subjected to semantic review by using a lightweight multi-modal large model, so that false alarms are inhibited. And efficient deployment of edge equipment is realized through a model quantification technology. Experiments show that the mAP50: 95 is improved by 2.84% on a self-built data set, and the recognition accuracy and the system reliability are remarkably improved while low delay is kept.

This invention relates to the fields of network security and deep learning, specifically a Tor website fingerprinting method for satellite internet. It achieves this by constructing a self-supervised contrastive learning framework to generate multi-view augmented samples; extracting temporal-granularity feature matrices; generating synthetic negative samples based on linear interpolation, which are then compared with positive samples to form contrast pairs; extracting trajectory representations; and jointly optimizing the results using cross-entropy loss and mask reconstruction loss. Compared to traditional website fingerprinting methods, this invention enhances the model's robustness to satellite-borne inherent noise caused by the Doppler effect. The weakly and strongly augmented views of this invention provide multi-scale semantic features, while the synthetic negative samples improve inter-class discrimination and reduce the false positive rate. The joint loss optimization framework allows the model to consider both global statistical characteristics and local burst features, significantly improving the accuracy and adaptability of website fingerprinting under the conditions of highly dynamic topology and limited annotation in satellite internet constellations.

This invention proposes a method for quality evaluation and multi-class discrimination of yam based on PCA and LDA, belonging to the technical field of agricultural product quality evaluation. The method includes the following steps: A) Constructing a discrimination model, specifically including A1) Data acquisition; A2) Data preprocessing and feature selection; A3) Constructing a linear discriminant model; B) Distinguishing yam categories, B1) Measuring 12 original indicator data of the sample to be tested according to the method described in A1); B2) Calculating the 12 original indicator data x... j Standardized to Z j B3) Z j Substitute the values ​​into the LDA discriminant function to calculate the values ​​for each type of yam; compare them, and the category corresponding to the maximum value is the discrimination result. When users apply the discrimination method of this invention, they do not need to understand the principle of PCA; they only need to perform simple standardization and a single linear combination calculation to complete the classification, which greatly reduces the threshold for using the model and the computational cost.

The invention discloses a class incremental learning method based on feature correlation and space structure preservation, and belongs to the technical field of machine learning. In order to solve the problems that the relieving effect of the disastrous forgetting problem in sample-free class incremental learning is limited and the class discrimination in an embedded space is difficult to maintain, a class incremental learning model based on feature correlation and space structure maintenance is established; training the class incremental learning model by using the incremental task to obtain a trained class incremental learning model; after each increment stage is completed, the trained model is used for testing to obtain a final class increment learning model, and the final model is used for class increment learning, so that the limitation of a traditional classification method in a dynamic learning environment is overcome, effective learning of newly added classes and long-term maintenance of historical knowledge are realized, and the learning efficiency is improved. And a more flexible and robust incremental learning capability is provided for the model.

The application provides a kind of based on visual identification inference and the class incremental learning method and system of data playback, the method includes: S1, the pre-training main stem of visual identification image is frozen, and bottleneck type residual adapter is introduced;S2, the causal latent variable space is constructed, the inter-concept dependency is learned, and the cross-task causal structure is continuously stable through the plastic updating mechanism and sparse constraint;S3, original sample is not stored, only the statistical distribution of historical class in semantic and causal space is saved, and pseudo sample is generated to realize data-free knowledge playback;S4, progressive weight scheduling and inference period uncertainty fusion mechanism are designed, and dynamic balance new and old knowledge is selected reliable branch output to realize stable prediction.The application can simultaneously maintain old class discrimination ability, support new class effective learning and have the class incremental learning method of reasonable forgetting mechanism under the premise of not saving old data.

An information processing method, an information processing apparatus, and a computer program that extract features of an intermediate layer that reflects subtle features of input data and perform class discrimination of discriminated data are provided. The information processing method includes: (a) a process of preparing, for each of a plurality of classes, a known feature spectrum group obtained when a plurality of teaching data is input to a machine learning model of a vector neural network type; and (b) a process of performing class discrimination processing of discriminated data using the machine learning model and the known feature spectrum group. Step (b) includes: (b1) a process of calculating a feature spectrum from input of the discriminated data to the machine learning model; (b2) a process of calculating, for each of the plurality of classes, a class-based similarity of the feature spectrum to the known feature spectrum group; and (b3) a process of discriminating a class of the discriminated data from the class-based similarity.

The invention relates to a waste paper regenerated pulp impurity classification method and system based on multi-modal sensing, and the method comprises the following steps: S1, obtaining an original multi-modal signal set of waste paper regenerated pulp flow through sensing array detection; s2, the collected original multi-mode signal set is preprocessed, and an aligned multi-domain signal set is obtained; s3, based on the aligned multi-domain signal set, features are extracted and normalized, and a multi-modal feature vector is obtained; s4, inputting the multi-modal feature vector into improved multi-category discrimination for feature correlation modeling, and performing multi-category discrimination; s5, determining the specific position and quantity of the impurities in the detection channel by combining a spatial positioning algorithm according to the multi-class discriminant output classification information; and S6, according to the types of the impurities and the specific positions and the number of the impurities in the detection channel, removing the impurities through a linkage execution unit, and purifying the waste paper regeneration pulp flow. According to the invention, accurate removal of waste paper regenerated pulp impurities is effectively realized.

This invention provides a method, system, and application for interpreting all features of remote sensing images by integrating zoning control and hierarchical extraction. By innovatively introducing a zoning control network constructed from real geographic elements such as roads and waterways, the large-scale image interpretation task is decomposed into multiple independent geographic units, effectively avoiding the problem of extraction results contradicting geographical common sense. Simultaneously, this invention employs a hierarchical extraction mechanism, extracting features class by class within each zoning according to visual saliency. Each dedicated model only needs to learn to recognize a single or a few categories, fundamentally improving inter-class discrimination and overall extraction accuracy. Furthermore, by encapsulating all stages—data preprocessing, zoning generation, hierarchical extraction, and result fusion—into visual, programmable tool nodes, and uniformly scheduling and executing them through a workflow engine, this completely changes the shortcomings of existing technologies, such as fragmented processes and reliance on manual coordination, significantly improving the standardization of production and engineering application capabilities.

This invention provides a method and system for grouping flue-cured tobacco using feature channel weighting and dynamic loss control, relating to the fields of deep learning and flue-cured tobacco grading. The method involves acquiring images of flue-cured tobacco from N main groups using an image acquisition device to establish a flue-cured tobacco grouping dataset, where N is a positive integer. This dataset is then preprocessed to obtain a preprocessed dataset. A flue-cured tobacco grouping classification network (TGNet) is designed and trained on the preprocessed dataset to obtain a flue-cured tobacco grouping classification model. Based on this model, the grouping results are obtained. This invention solves the technical problems of existing deep learning methods for flue-cured tobacco grouping, such as lack of key feature representation in high-scale features, limited inter-class discrimination ability, and a tendency for the model to learn from majority class samples during training. It achieves real-time classification of flue-cured tobacco groups, effectively improving the efficiency of flue-cured tobacco group classification and reducing the cost of manual grading.