2185 results about "Detection performance" patented technology

The invention provides a multi-feature fusion rumor detection method, system and device based on knowledge distillation, and mainly solves the problems that an existing model is high in calculation overhead, insufficient in feature fusion and insufficient in emotion utilization. The method comprises the steps of firstly obtaining multi-dimensional data such as social media original texts and comments; extracting deep semantic representation by using a pre-training model, and analyzing comment emotion features in combination with a hybrid neural network; then, features such as semantics, emotions, emoticons and populations are input into a hierarchical gating interactive fusion network (GIFN), and weights are dynamically adjusted to achieve effective fusion of multi-granularity features; in order to reduce complexity, a knowledge distillation framework is designed: a deep GIFN is used as a teacher network to generate a soft label, and a lightweight student network (LSTM) is guided to perform training. According to the trained student model, the parameter quantity is remarkably reduced, meanwhile, good detection performance is kept, the student model can be conveniently deployed in an actual content auditing system or edge equipment, and social content rumors can be efficiently recognized and judged.

The invention provides a thin film surface defect detection method and system, and relates to the technical field of defect detection.According to the thin film surface defect detection method and system, an intelligent secondary verification link is constructed by introducing a defect confidence evaluation mechanism based on form and energy distribution, so that the detection performance is fundamentally improved; according to the mechanism, real physical defects with regular forms and concentrated energy and pseudo defects caused by electromagnetic interference, instantaneous film wrinkles and the like can be accurately distinguished, and the problem of high false alarm rate caused by dependence on single signal strength in the prior art is effectively solved while the high detection rate of low-contrast defects is reserved; besides, the judgment model based on physical characteristics has natural robustness for background noise generated in high-speed motion, and an adjustable confidence threshold value endows the system with extremely high practical flexibility, so that the system can adapt to complex and changeable industrial environments and different quality control standards, and the method is suitable for large-scale popularization and application. And the accuracy, the reliability and the intelligent level of the whole detection system are obviously enhanced.

The invention discloses an unmanned aerial vehicle aerial image target detection method based on PSO-DETR, and belongs to the technical field of unmanned aerial vehicle aerial image target detection. Firstly, a parallel patch perception attention feature extraction module is constructed, and an efficient multi-branch backbone network C3KCSPnet is designed by fusing a CSPDarknet53 structure; according to the network, gradient flow is improved through deep optimization, and the capturing capacity of high-level semantic information is enhanced. And secondly, an enhanced channel offset hybrid operator is provided, the dependency relationship between channels is enhanced through a channel shuffling mechanism, and cross-channel interaction of local space information is realized in combination with channel offset operation, so that the feature recovery quality and fusion efficiency in an up-sampling stage are improved, and the problem of missed detection of a shielded target is further relieved. And finally, a re-parameterization hierarchical aggregation network is designed, effective integration of shallow details and deep semantics is realized through an efficient hierarchical fusion mechanism on the premise of ensuring controllable calculation complexity, and the detection performance of the small target is further enhanced.

The invention relates to the technical field of semiconductor manufacturing, in particular to a semiconductor defect detection method and system based on deep learning. The method comprises the following steps: step 1, multiband cooperative imaging and dynamic scanning control; 2, performing multi-scale feature fusion and defect identification; 3, dynamic threshold judgment and multi-scale feature fusion network optimization: dynamically adjusting a judgment threshold according to probability distribution characteristics of a current batch defect thermodynamic diagram, applying an offset to the threshold in combination with a wafer process type, and determining the offset according to a balance relationship between a false drop rate and an omission rate in historical data; critical samples and misjudgment samples with classification confidence close to a threshold value in historical detection are periodically screened, incremental learning is performed on the last layer of the multi-scale feature fusion network, and upstream network weight is frozen to prevent feature drift. Through fine image processing, multi-band information fusion, dynamic threshold adjustment, incremental learning and other mechanisms, the defect detection efficiency and accuracy in the semiconductor manufacturing process can be effectively improved, and the detection performance is continuously optimized.

The invention discloses a semi-supervised multi-temporal satellite image time-varying information extraction method, and belongs to the technical field of remote sensing image processing. The semantic change detection performance of the model and the detection precision of complex shape change ground objects are improved. The method comprises the following steps: constructing a semantic change detection model, carrying out full-supervised training on the semantic change detection model by using a binary change detection supervised loss function and a semantic segmentation supervised loss function by using a small amount of labeled dual-temporal remote sensing images to obtain an initial model, and obtaining a semantic change detection prediction result of each pair of images; using a pseudo label optimization strategy to optimize the semantic change detection prediction result of each pair of images; combining the obtained pseudo label data with high confidence and a small amount of labeled dual-temporal remote sensing images into a new training set, using the new training set to perform semi-supervised training on the initial model in a semantic change detection model, and using a consistency regularization combination loss function to perform supervised training to obtain a new model; and until a preset number of iterations is reached.

The invention discloses a multi-scale context enhancement small target detection method based on an improved RT-DETR (Reverse Transcription DET Rate). The method comprises the following steps: preprocessing unmanned aerial vehicle image data, and then constructing an improved RT-DETR model; the core is that a CSP-GFCG feature extraction module is used for modulating a feature map through frequency domain transform (DFT / IDFT) and a learnable global filter by using GFNet to realize global context modeling; and then the processed features are input into a ConvGLU module, and local features are enhanced in combination with depth separable convolution and a gating linear unit. GFNet and ConvGLU cooperate with each other, and challenge is effectively reserved for scale change and details in small target detection. The method aims at optimizing a feature extraction mechanism, reducing redundancy and improving the detection performance of a small target under a complex background. Meanwhile, the calculation efficiency is improved, the resource consumption is reduced, and the problem of missing detection of small targets is effectively solved.

The invention provides an aluminum film sealing defect real-time detection method and system based on multi-algorithm fusion, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: triggering an industrial camera at a detection station to collect an original image of a pesticide aluminum film sealing on a conveyor belt; performing adaptive equalization operation on the original image through pixel brightness distribution data, eliminating light fluctuation and surface reflection interference, and outputting a standardized image; three types of defect detection are synchronously executed based on the standardized image, a dynamic threshold segmentation algorithm is combined with local area brightness analysis to detect edge damage, a contour extraction algorithm is adopted to calculate bottleneck center offset to recognize seal offset, wrinkle defects are recognized based on a surface texture feature analysis algorithm, and a primary detection result is output. The aluminum film sealing defect detection method is based on multi-algorithm fusion, has strong anti-interference capability, real-time detection performance and data traceability, and provides an efficient and reliable automatic solution for aluminum film sealing quality management and control.

The invention relates to a multi-modal sparse fusion three-dimensional target detection method in an unstructured environment, and the method is based on a complexity perception candidate region dynamic sampling strategy, and through the cross-domain self-compensation of point cloud geometric features and image spectral features, and the fusion of multi-view sparse features, the detection of a multi-modal sparse fusion three-dimensional target is realized. The perception capability and the recognition precision of the obstacle area, and the remote dynamic target detection performance and the real-time performance are improved; an anti-deformation convolution group and a terrain gradient perception attention module are introduced into a ParScaleNet image backbone network, so that the extraction of edge features of a complex scene is enhanced, and the cross-scale characterization capability of the features is improved; according to the method, a ContraSpaceOpt module with semantic maintenance capability is deployed behind a Transform, excessive smoothness of obstacle features is inhibited through class comparison loss functions and feature space anisotropy constraints, the space separability of obstacles is maintained, and the problems of point cloud fracture and texture misalignment caused by the obstacles are effectively solved.

The invention discloses a network intrusion detection method and system based on edge attention learning, and a storage medium, and the method comprises the steps: converting an original network flow into a network flow diagram, and constructing a training diagram and a test diagram under the condition that a coarse-grained label and a fine-grained label are reserved; edge embedding representation is obtained through edge feature reservation, adaptive weight distribution and multi-layer feature extraction of the training graph and the test graph; based on the edge embedding representation, performing coarse-grained detection to identify a basic attack category, and performing fine-grained classification by using multi-scale feature fusion related to global graph attributes; and adversarial training: through initializing adversarial disturbance and optimizing disturbance based on loss function gradient iteration, superposing final disturbance into the training graph, and based on loss function back propagation updating, obtaining a trained network intrusion detection model. The method provided by the invention can effectively capture the depth characteristics of the key attack and maintain the stable detection performance in the confrontation environment.

The invention relates to the technical field of intelligent traffic supervision, and discloses a vehicle tarpaulin coverage real-time detection method based on multi-modal feature fusion, and the method comprises the following steps: S1, constructing a bimodal input data stream; s2, the bimodal images are preprocessed respectively; s3, extracting features; s4, dynamically fusing the bimodal features through an adaptive feature fusion module; s5, inputting the mixed feature map into a lightweight convolution detection network, and outputting a segmentation mask; s6, motion trail compensation is carried out on the dynamic vehicle; by designing a multi-modal adaptive feature fusion mechanism, the robust detection performance in a complex environment is improved: the fusion weight is dynamically adjusted based on the environment illumination and the temperature gradient, so that the system automatically strengthens effective modal features under extreme conditions such as strong light, night, rain and fog and the like; by introducing a dynamic motion compensation framework, the problem of motion fuzzy interference of a running vehicle is effectively solved, and the boundary precision of dynamic vehicle tarpaulin coverage detection is improved in a breakthrough manner.

The invention discloses an industrial Internet of Things time sequence self-supervision anomaly detection method and a monitoring and early warning system, and relates to the field of industrial Internet of Things, and the method comprises the steps: S1, constructing an anomaly detection model, and S2, obtaining a training data set; s3, training and optimizing an anomaly detection model; s4, acquiring to-be-detected data in real time; s5, performing anomaly detection analysis on the to-be-detected data, and outputting an anomaly detection result; through a time sequence and relation learning module, a dynamic graph topological structure learning module and an enhancement module, internal characteristics of a time sequence in a time domain and a space domain are deeply mined. The time sequence and relation learning module comprehensively captures a multi-scale time pattern, and the dynamic graph topological structure learning module eliminates dependence on a predefined graph structure; the enhancement module enhances the invariant representation under noise, and improves the recognition capability of the model to a normal mode; through wide experiments, the advancement of the method in detection performance is verified, and reliable support is provided for intelligent manufacturing and infrastructure diagnosis.

The invention discloses an industrial product surface defect detection method based on feature coupling, and the method comprises the steps: 1) constructing a four-stage backbone feature extraction network, and integrating a DPSC module to expand a receptive field, thereby achieving the gradual feature learning from local to global; 2) designing a multi-scale feature fusion network, realizing effective fusion of different scale features, and performing deep coupling on high-level semantic information and low-level detail information; 3) constructing a multi-branch detection head to realize full-scale coverage; and 4) performing end-to-end training optimization: calculating a weight importance score by applying an LAMP pruning strategy, deleting redundant parameters, and remarkably reducing the model complexity and the calculation cost while keeping the detection performance. According to the method, through a global-local feature coupling mechanism, the technical problems that in industrial product surface defect detection, the defects are highly similar to the background, and the scale change is large are effectively solved, and high-precision and high-efficiency defect detection is achieved.

The invention discloses a pavement throwing detection method and device based on deep learning, electronic equipment and a program product. The method is realized through a trained detection model, the model adopts an LMSADet detection head, a multi-scale feature extraction and space attention mechanism is introduced into a task branch, and multi-scale modeling is decoupled from a backbone network and a neck network and integrated to the detection head so as to fit a detection task to directly optimize local details and scale differences of a throwing target. In order to suppress background interference and improve the recognition effect of fuzzy boundaries, the neck network is added into an MSHA module so as to efficiently capture the semantic relation between the thrown object and the background and enhance the regional understanding ability. A C3ESP module is introduced into the backbone network, deep features are extracted through stacking depth separable convolution, and information loss is avoided in combination with residual optimization fusion; meanwhile, a PEMA attention mechanism is introduced, the importance of different receptive field features is dynamically adjusted, the model focuses on key features, data information is captured more comprehensively, and therefore the detection performance is remarkably improved.

Systems and methods for dynamic invocation of synthetic probes based on Real User Monitoring (RUM) agents include monitoring application performance metrics using a Real User Monitoring (RUM) agent embedded within a client application, wherein the RUM agent continuously observes and reports metrics indicative of user experience; detecting performance anomalies by analyzing application and network metrics against baseline performance thresholds established during normal operations; and initiating dynamic synthetic probes in response to the detected anomalies, wherein said synthetic probes are adaptively configured to target relevant destinations, adjust probing frequency, and utilize specific probing methods tailored to the characteristics and severity of the performance anomalies.

The invention provides an underwater sonar target detection system and method. The underwater sonar target detection system comprises an optical fiber hydrophone array module which comprises a plurality of optical fiber hydrophone units, each unit comprises an optical fiber Bragg grating sensor and a sound pressure signal demodulation device, and the optical fiber hydrophone array module is used for collecting underwater sound wave signals in real time and converting the underwater sound wave signals into first electric signals; the sonar transmitting-receiving array module comprises a broadband sonar transmitter, a multi-beam receiver and a signal preprocessing circuit, and is used for actively transmitting a frequency modulation continuous wave signal, receiving a target reflection echo and generating a second electric signal; and the multi-mode signal fusion processing module comprises a high-speed data acquisition card, a self-adaptive noise suppression unit and a time-frequency analysis unit. The underwater sonar target detection system and method provided by the invention have the advantages of relatively high reliability, relatively high detection performance, relatively accurate cross-modal signal fusion and capability of performing intelligent target identification and tracking.

The invention discloses a weak supervision video anomaly detection method based on prompt learning knowledge enhancement, and belongs to the technical field of video intelligent analysis. A video side gives a section of abnormal scene video, video sequence features and audio sequence features are obtained through a feature extraction network, then a trained and complete feature aggregation network is input to carry out multi-modal feature aggregation, an abnormal score is obtained through a score prediction network, and text representation is carried out based on prompt learning. A prompt template is constructed for abnormal video tags through a knowledge graph, semantic expansion is performed on normal tags through a plurality of learnable parameters, cross-modal alignment is performed on the normal tags and a video side, so that features of the video side are close to different normal semantics, knowledge enhancement is performed by introducing external information, positive abnormal boundaries of the video are learned, and the detection performance is improved. And finally, multi-task joint optimization is carried out through different loss functions, and abnormal video clip positioning is carried out.

The invention relates to a multi-modal sparse fusion three-dimensional target detection method in a structured environment, and the method comprises the steps: carrying out the cross-domain self-compensation of point cloud geometric features and image spectral features, and carrying out the fusion of multi-view sparse features; the perception capability and the recognition precision of a long-distance target, a complex shielding target and a small-scale target, and the detection performance and the real-time performance of a long-distance dynamic target are improved; a novel ParScaleNet image backbone network is designed, and a parallel multi-branch structure is introduced to enhance the multi-scale feature representation capability and the channel dependency relationship modeling capability; a staged progressive feature fusion strategy is adopted, hierarchical feature interaction is realized on a fine-grained spatial scale, and a cross-channel adaptive weighting mechanism is combined, so that the network can efficiently extract and focus key features, the feature expression ability of the model is improved, the stability and robustness of detection precision are ensured, and the detection accuracy is improved. And high-efficiency and high-precision target detection in a structured road scene is realized.

The invention discloses an underwater low-resolution small-target biological detection method based on an improved pyramid. The underwater low-resolution small-target biological detection method comprises the following steps: firstly, dividing a public underwater image data set into a training set, a verification set and a test set in proportion; then constructing a GPBS-YOLOv8 model, and replacing a C2f structure with a PPA module in a backbone network to enhance multi-scale features; introducing a GSConv module at the neck to reduce parameter quantity and optimize feature representation; in the feature fusion stage, a BiFPN capable of learning weight is adopted, and a P2 small-scale detection layer is newly added; shape-IoU loss is used to improve shape regression accuracy. And finally, training the model on a training set, and verifying the real-time and high-precision detection performance of the model on a low-resolution small target in a complex underwater environment on a test set.

The invention discloses a camouflage target detection method based on feature selection attention and frequency domain edge guidance. According to the method, four-level features of a camouflage target image are extracted through a backbone network SMT and are respectively screened; the high-level features are input into a semantic information supplement module, and after semantic features are enhanced, the high-level features and the trunk features are sent into a spatial feature enhancement module together. And inputting the obtained fine-grained features into an edge feature sensing module, and finally fusing multi-scale features through a multi-scale jump connection technology to generate a mask pattern with higher discrimination. The method has the advantages that the network parameter quantity is reduced and key information is reserved through a feature selection mechanism; a spatial feature enhancement module is used for enhancing multi-scale feature representation and remote dependence modeling; the dilution of the semantic context is relieved by means of a semantic supplement module so as to improve the positioning precision; and an edge feature enhancement module is adopted to enhance edge semantic perception and improve boundary integrity. According to the method, the camouflage target detection performance is remarkably improved with relatively low calculation cost.

The invention belongs to the field of three-dimensional target detection, and particularly relates to a lightweight Mama three-dimensional target detection method based on columnar point cloud representation, which mainly consists of three parts: a spatial feature processing module based on Hilbert serialization and dynamic grouping, a Mama module based on a selective state space and a lightweight pyramid feature fusion module. The Hilbert serialization module keeps spatial locality through a serialization mode, and is helpful for capturing a structural relationship between adjacent points in the point cloud, so that the modeling effect of local feature integration and context information is improved; the Mama module adopts an input-dependent dynamic modeling mechanism, can provide higher modeling efficiency and stronger long-range dependent modeling capability when processing a large-scale volume column sequence, and is particularly suitable for a sparse point cloud scene; the lightweight pyramid fusion module enhances the perception capability of a target boundary through single-round up-down sampling and feature fusion, and improves the detection performance of a small target, thereby effectively balancing the efficiency and precision of 3D target detection.

The invention discloses a camouflage target detection method for a hierarchical semantic aggregation network of deep guide frequency domain perception. The method is specifically implemented according to the following steps: step 1, constructing a data set and extracting camouflage target features through a Sam2 trunk; step 2, constructing a depth-guided amplitude spectrum fusion module; step 3, constructing a layered feature fusion-local feature reconstruction module; and step 4, respectively inputting the feature vectors obtained in the step 2 and the step 3 into a mask-guided attention feature fusion decoder, and finally analyzing and outputting a result. According to the method, the masks output through coarse positioning and local reconstruction serve as priori knowledge and are combined with the features fused with depth information to be input into the mask attention decoder, key information of the camouflage object is further mined and recognized, the problem that the detection performance of the camouflage object is degraded in an existing complex scene is solved, and the detection efficiency of the camouflage object is improved. High detection precision can still be kept in a complex scene, and methods and systems of artificial intelligence and computer vision are enriched.

The invention discloses a streaming detection method for harmful output of a large language model, and the method comprises the steps: carrying out lexical element level labeling on the collected harmful output of the large language model, and obtaining lexical element level labeling data; based on the lexical-level annotation data, a multi-task learning framework is adopted to train a streaming detection model, and the streaming detection model comprises a feature extractor, a global scoring device and a lexical scoring device; and carrying out stream detection on the stream detection model along with the lexical element output stream of the large language model, and detecting and judging the output harmfulness in the output process of the large language model according to a threshold value set by a user so as to realize stream detection based on incomplete output. According to the method, the harmful output stream is stopped in advance while the detection performance is ensured.

The invention relates to the technical field of sensors, and discloses a detection and management method and system for purification equipment. The method comprises the following steps: carrying out three-phase coupling dynamic modeling on a gas phase flow state, a particle phase movement track and a sensor phase interface characteristic in the purification equipment to obtain a gas mass transfer characteristic parameter; performing response characteristic analysis on a real-time detection signal of a sensor array in the purification equipment to obtain a sensor calibration compensation parameter; based on the sensor calibration compensation parameters and the gas mass transfer characteristic parameters, deposition kinetics analysis of pollutants on the surface of the sensor is carried out, and equipment operation state evaluation data are obtained; and performing spatial layout optimization on the sensor array according to the equipment operation state evaluation data and the gas flow consistency constraint condition to obtain an optimal layout scheme and generate a staged adaptive management control instruction. According to the invention, self-adaptive adjustment and intelligent switching of the sensor management strategy are realized, and the detection performance and reliability of the purification equipment sensor system are significantly improved.

The invention provides a differential Mama-based adaptive background reconstruction hyperspectral anomaly detection method, and solves the problem of poor detection performance caused by insufficient local detail reconstruction precision in the prior art. Comprising the following steps: 1) acquiring an original hyperspectral image, and dividing the original hyperspectral image; 2) constructing an adaptive background reconstruction hyperspectral anomaly detection model which sequentially comprises an encoder, a differential state space DSSM model, a weight-guided center feature reconstruction WCBR module, a space-spectral attention SSA module and a decoder based on a traditional differential Mamba architecture; 3) adopting an L2 norm as a loss function of the detection model, and guiding the model to be trained to converge; and 4) inputting the original hyperspectral image into the trained final detection model to obtain a reconstructed hyperspectral image, and calculating to obtain an anomaly detection result. According to the method, the background reconstruction effect can be improved, abnormal feature expression can be remarkably inhibited, and the hyperspectral anomaly detection performance is effectively improved.

The invention discloses a road vehicle detection method based on high-frequency edge feature enhancement, which is characterized in that on the basis of a YOLOv11n model, an MSFE-C3k2 module is designed to replace a C3k2 module in a backbone network, and the perceptual ability of the model to target edge features is improved. An ASFPN structure is introduced into a Neck part, the multi-scale feature expression ability of the model is effectively enhanced, and the learning ability of small target vehicle features is further optimized in combination with a small target detection head. And a shared detection head SEHead is designed, so that the parameter quantity is effectively reduced while the detection precision is improved. And finally, a WMIoU loss function is proposed to replace the original CIoU, so that the bounding box regression precision is further improved. According to the method, the detection performance of the small target vehicle can be remarkably improved by strengthening the high-frequency edge features, and the regression precision of the model bounding box is optimized.

The invention discloses a remote sensing image small target identification method based on improved YOLOv8, and the method comprises the steps: obtaining a remote sensing image data set, carrying out the preprocessing, and generating a preprocessed data set; an improved YOLOv8 model is constructed, the improved YOLOv8 model comprises a backbone network, a neck network and a head network, the head network comprises a small target detection layer, the improved YOLOv8 model adopts an EIoU loss function to measure the difference between a real frame and a prediction frame, a regression weighted non-maximum suppression method is adopted to perform weighted averaging on the position of the prediction frame, and the position of the prediction frame is corrected; training an improved YOLOv8 model based on the preprocessed data set to obtain a trained model; and performing small target identification detection on the remote sensing image based on the trained model, and outputting a detection result. The invention further discloses a remote sensing image small target recognition device based on the improved YOLOv8, corresponding equipment and a storage medium. According to the invention, missing detection and false detection of small targets in remote sensing images can be effectively reduced, and the detection performance is improved.

The invention discloses a network intrusion detection method and system based on dynamic graph attention and comparative learning. Network traffic is constructed into a dynamic heterogeneous graph (nodes are IPs / ports, and sides are traffic sessions), and dynamic feature fusion is carried out by adopting time window division and a GATv2 network. An optimal transmission contrast learning strategy is innovatively introduced, feature and structure distribution alignment is realized through a Wasserstein distance and a Gaussian Wasserstein distance, and the generalization ability of the model to unknown attacks is improved. And finally, combining node embedding and an alignment matrix, and utilizing an MLP classifier to predict an edge anomaly probability. Experiments show that the accuracy and F1-score of the method on multiple data sets are improved by 5.2%-10.5% compared with those of a baseline, the detection performance under complex attacks is remarkably enhanced, and the method is suitable for real-time scenes such as the Internet of Things. The system can be deployed on edge equipment and has high practical value.

The invention discloses a rice leaf tip small target detection and counting method based on global information enhancement, and the method comprises the steps: firstly building a field rice leaf tip image data set as a basis, and constructing an improved YOLO-DCL model; the core innovation of the method lies in that a global context information enhancement module, an inverted residual-cascade grouping attention module and a re-parameterization shared convolution detection head are introduced, key feature expression is enhanced and detection efficiency is optimized through effective fusion of global information, the recognition precision and processing speed of the model on a tiny rice leaf tip target are significantly improved, and the method is suitable for large-scale popularization and application. After training parameters are set, an optimization model is trained, then system performance verification and module optimization are carried out on the model, and a version with the optimal rice leaf tip detection performance is screened out. The technical bottlenecks that small target leaf tips are prone to missing detection and false detection and insufficient in real-time performance under the complex farmland background are effectively overcome, and reliable and efficient technical support is provided for rice growth early-stage yield prediction.

The invention discloses a data-enhanced fine-grained multi-mode false information detection method and system, and aims to improve the accuracy of image-text false news detection. The method comprises the following steps: acquiring a news text and associated pictures thereof, extracting a text core entity semantic sequence and a visual entity semantic sequence by respectively utilizing a pre-training language model and a visual entity recognition model, and performing knowledge enhancement on original word-level text representation and low-level visual features through an attention mechanism; calculating a correlation matrix between the enhanced text and the visual features, dividing consistent and inconsistent regions, and respectively extracting consistent and inconsistent features; and finally, fusing the two types of features and global text representation to generate classification features so as to judge the authenticity of the news. Through double-channel knowledge enhancement and fine-grained cross-modal consistency analysis, the detection performance is remarkably improved, and the method is suitable for scenes such as social media and news platforms.

The invention discloses a camouflage target detection method and system based on a double-domain fusion enhanced network, and relates to the technical field of target detection. Through the nonlinear double-domain fusion module, in combination with nonlinear mapping of a spatial domain and a frequency domain, key difference characteristics of a frequency domain amplitude spectrum and a phase spectrum are captured, the problem that the detection performance is reduced in a scene of low contrast and the like depending on an RGB spatial domain is solved, and the target discrimination degree is improved; based on a lightweight scale perception modulation converter and a double-feature fusion module, multi-scale features are extracted, aligned and fused, a semantic relation is integrated by means of cross attention, and the problems of detail loss and boundary fuzziness caused by scale diversity are solved; the context feature enhancement module integrates cross attention and edge auxiliary injection, accumulates multi-layer feature integration, gives consideration to a global boundary and a local structure, effectively reduces false detection, missing detection and edge roughness, and further enhances robustness through multi-layer auxiliary supervision.