7 results about "Basic class" patented technology

The invention provides a fine configuration method and system based on a strategy mode, and the method comprises the steps: defining themes used for abstracting entrance traffic, order distribution and other events through a configuration system, and configuring a basic data source and a data processing rule for each theme, wherein the data processing rule supports a user to carry out code development implementation in a basic class of each service line according to service requirements; the system automatically stores theme data to middleware, matches a corresponding theme through a strategy mode after receiving a user request, performs secondary data processing according to a configuration rule and returns a result; the technical effects of flexible configuration mode, quasi-real-time index calculation, support of multi-source data access, high-concurrency scene adaptation and good expansibility in flow fine management are realized, and the service operation demand change can be quickly responded.

The invention discloses a real-time open vocabulary video target detection method based on efficient time sequence aggregation and knowledge migration, and relates to a computer vision technology. The problems of poor real-time performance, weak generalization ability of novel categories, insufficient stability of cross-frame detection and the like in the prior art are solved. Firstly, a sparse sampling strategy is adopted to select key frames to reduce calculation overhead; secondly, an enhanced supervision set is constructed, and a basic category real label and a novel category pseudo label generated by a teacher model are fused; extracting multi-scale anchor-level features through a backbone network, and aggregating time sequence features through an anchor-level memory attention module; and finally, reasoning by adopting a label space expert mixed strategy, and optimizing the model in combination with a multi-task loss. Compared with the prior art, the method has the advantages that excellent performance-efficiency balance is achieved, the method is outstanding in performance on data sets such as LV-VIS and BURST, the reasoning speed is increased by 70-120 times compared with an existing method, meanwhile, the robustness to novel categories and specific video challenges is enhanced, and the method is suitable for real-time application scenes such as intelligent monitoring and automatic driving.

This provides a machine learning technique that can suppress overfitting of new knowledge when applying IFSL to SaB. [Solution] This disclosure provides a machine learning device 100 that performs continuous learning based on a small number of new class data compared to basic class data, comprising: a pre-training module 30 that learns the weights of a neural network (NN) using basic class data; a pseudo-continuous learning module 40 that learns the weights of the NN learned by the pre-training module 30 using pseudo-data generated based on the basic class data; and a new class learning module 50 that learns the weights of the NN learned by the pseudo-continuous learning module 40 using basic class and new class data.

The application provides a so file hook method, device and readable medium based on a loading program library, the method comprises the following steps: acquiring all loading path information of a so file and acquiring difference path information; establishing an interface for providing data of a storage path, storing the difference path information; establishing an interface for providing exclusion path data, and encapsulating the interface for providing data of the storage path and the interface for providing exclusion path data through a basic class; acquiring a function name to be hooked and a name of a replacement function; then finding the basic class to parse a so file related to the function to be hooked; judging that the so file related to the function to be hooked is running through a loading program database, and performing a hook operation, so that the so file to be hooked can be quickly found and excluded.

The weakly supervised temporal action localization method and device based on semantic and saliency knowledge collaborative propagation comprises the following steps: 1) extracting temporal features and saliency foreground features from an uncropped video; 2) constructing a basic branch and a saliency perception branch to respectively process the temporal features and the saliency target features to obtain a basic class activation sequence, a motion, appearance representation score and a saliency class activation sequence, and weighting and fusing the four sequences to obtain a fused action score sequence; 3) utilizing branch distillation and branch action consistency constraint to interact semantic information and saliency information, and perfecting the fused action score sequence; 4) extracting key segments and ambiguous segments of the basic branch and the saliency perception branch, and utilizing the key segments and the ambiguous segments between branches and within branches for comparative learning to improve feature representation, combining the distillation result to perfect the fused action score sequence and obtaining an action localization result. The present application can perceive subtle human actions and accurate temporal action boundaries in uncropped videos.

The application discloses a SAR image incremental small sample target detection system and method based on prototype contrast, and the system comprises a class prototype representation generation module, a mixed class prototype contrast coding module, a class prototype calibration module and a target detection module; the class prototype representation generation module is used for extracting a basic class RoI feature mean value of a historical SAR image as a class prototype based on a pre-training model; the mixed class prototype contrast coding module is used for designing a loss function in combination with a new class sample and the class prototype, forcibly aggregating the same class and separating different classes, and optimizing a feature space; the class prototype calibration module is used for measuring and minimizing distribution differences between the new class sample and the class prototype through a Gaussian kernel function, constraining representation deviation in an incremental stage, and obtaining an InFSAR model; and the target detection module is used for acquiring a SAR image and performing small sample target detection based on the InFSAR model.

The application discloses a small sample target detection method based on contrast learning and multi-aspect distillation, constructs a small sample target detection network model based on contrast learning and multi-aspect distillation, carries out basic class basic training on the small sample target detection network model, obtains a small sample target detection basic class model, carries out new class fine-tuning training on the small sample target detection basic class model, obtains a final small sample target detection model, and finally detects small sample targets according to the final small sample target detection model. The method solves the problems that the traditional target detection method is prone to class confusion and weak information capturing capacity, greatly improves the capturing capacity of the detection model on target features, simultaneously strengthens foreground representation and reduces the interference of background information, and improves target detection performance.