Small Object Detection (SOD) aims to accurately identify and locate small objects in images. However, existing methods usually focus on exploring spatial domain features, neglecting high-frequency features that preserve fine-grained details such as texture and edge information. To overcome this limitation, we propose a High-Frequency Feature-Oriented Network (HFFO-Net). First, we introduce the Channel- wise Frequency Modulation Module (CFMM), which leverages the 2D Discrete Cosine Transform (DCT) to accentuate salient frequency components while mitigating noise interference. Second, we design a High-Frequency Oriented Module (HFOM), which utilizes the Channel Selection Branch (CSB) and Spatial Selection Branch (SSB) to highlight small objects in the channel and spatial region. Third, we introduce a Dual-Query Attention Fusion Mechanism (DQAFM), which reduces the semantic gap between spatial and frequency features and achieves better feature fusion through bidirectional cross-attention. Extensive experiments are implemented, and the corresponding results demonstrate that HFFO-Net excels at detecting small objects.

The purpose of multimodal industrial anomaly detection is to detect complex geometric shape defects such as subtle surface deformations and irregular contours that are difficult to detect in 2D-based methods. However, current multimodal industrial anomaly detection lacks the effective use of crucial geometric information like surface normal vectors and 3D shape topology, resulting in low detection accuracy. In this paper, we propose a novel Geometric Prior-based Anomaly Detection network (GPAD). Firstly, we propose a point cloud expert model to perform fine-grained geometric feature extraction, employing differential normal vector computation to enhance the geometric details of the extracted features and generate geometric prior. Secondly, we propose a two-stage fusion strategy to efficiently leverage the complementarity of multimodal data as well as the geometric prior inherent in 3D points. We further propose attention fusion and anomaly regions segmentation based on geometric prior, which enhance the model’s ability to perceive geometric defects. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the State-of-the-art (SOTA) methods in detection accuracy on both MVTec-3D AD and Eyecandies datasets.

Few-shot relation extraction aims to identify and classify specific semantic relations between entities from text with a small number of annotated examples. Recent studies have shown that innovative model designs and learning strategies can significantly enhance the model’s generalization ability and performance, even with limited training samples. However, the samples used for training face the dual challenges of scarce annotated data and semantic ambiguity. Given the limitations of the existing SaCon framework in negative sample generation and discrimination efficiency, we propose a dynamic adversarial negative sample enhancement strategy. This strategy introduces adversarial perturbations before encoding the pre-trained language model by constructing a multi-granularity semantic space. Specifically, we first design an entity permutation mechanism to randomly exchange the subject/object entities of sentences in a small batch to generate negative sample clusters with similar semantics but misplaced relations, then, we integrate a multi-view contrastive learning framework to embed adversarial samples into the feature space topology optimization process.To strengthen boundary-sensitive features, an adaptive margin ranking loss function is proposed to dynamically adjust the representation distance constraints of positive and negative samples, forcing the model to capture the deep semantic invariance of relational predicates under limited samples. This method aims to optimize the traditional negative sample random sampling paradigm, actively explore the semantic space through an adversarial generation mechanism, and construct “difficult samples” with minimal semantic deviation through gradient back propagation, thereby improving the model’s ability to parse implicit relational patterns. The experiment result shows that this framework effectively alleviates the risk of overfitting in small sample scenarios by decoupling relational semantics and surface syntactic features, and its dynamic loss design provides mathematical guarantees for orthogonal separation of feature space. Our code is available online at https://github.com/hhy-test/ESCR.

In the Distantly Supervised Relation Extraction (DSRE) task, it is typically assumed that sentences containing the same entity pair reflect the same relation. While this assumption simplifies the learning process to some extent, it inevitably introduces substantial noise. Previous extensive research has utilized a series of selective attention mechanisms on sentences in the bag to extract relation features, but has seldom considered leveraging the information surrounding the entities and different features. We argue that tokens surrounding the entities play a significant role in relation classification, though their importance varies. In this paper, we propose the Dynamic Semantic Interaction (DSI) module, which uses token-level features to calculate the similarity between the entity and other tokens in the sentence as weights, assigning different importance to each token. Additionally, the Responsiveness Feature Fusion Strategy (RFFS) uses Euclidean distance to calculate reliability scores, adaptively adjusts the information fusion process, and weights different features to reduce the impact of noisy information. Finally, the Relation-Aware Contextual Modeling (RACM) module initializes and trains a set of seed vectors to guide the model in focusing on relation-relevant contextual features, thereby improving relation recognition. Combining these methods, our model is able to better predict the relations between entity pairs. Experimental results show that our model demonstrates significant advantages across various mainstream DSRE datasets.

While current multimodal anomaly detection methods predominantly employ intermediate fusion strategies, they often suffer from inadequate cross-modal interaction and irreversible information loss during feature alignment processes. To overcome these limitations, we propose Hierarchical Geometry-Color Fusion (HGCF), a novel framework that establishes deep synergistic relationships between RGB texture features and point cloud geometric representations. Firstly, we propose a bidirectional cross-modal early fusion mechanism that enables complementary information exchange between point cloud and RGB modalities at the input level. Secondly, we introduce a local self-supervised geometric color reconstruction network with group-wise feature alignment, enhancing fine-grained feature extraction through joint color-geometry reconstruction tasks. Finally, we propose a local window spatial-consistent attention fusion, which achieves semantic consistency and spatial consistency by emphasizing local mutation features to improve the detection of subtle anomalies. Extensive experiments show our model achieves 99.1% I-AUROC on MVTec 3D-AD and 91.7% on Eyecandies, both surpassing state-of-the-art methods.

Near-infrared transmission through the finger can capture the vein structure for identity recognition. However, in outdoor applications, finger vein imaging is significantly affected by environmental illumination resulting in low recognition performance. Existing methods typically address this issue by constructing multi-illumination models, but collecting multi-illumination images from individual is challenging, and overexposure can cause venous structure distortion. This paper proposes MDA-Net, a Multi-illumination Domain Adaptive Network for finger vein recognition, which is engineered to excel in the dynamic outdoor lighting landscape with various conditions including overexposure, using only data collected under a single illumination for training. Firstly, an Illumination Feature Separation Network(IFSNet) is used to remove the illumination components and obtain illumination-invariant features; Then an Absorption Difference Feature Extraction network(ADFENet) is used to reduce the impact of venous structure distortion under illumination conditions, especially overexposure. To replicate the entire range from low-light to overexposure in outdoor scenarios, a novel Multi-Illumination Finger Vein Dataset (MIFVD) is constructed with significant illumination variations. Experimental results show that MDA-Net significantly improves recognition performance under complex illumination conditions, achieving a state-of-the-art (SOTA) average recognition rate of 91.67% and an average equal error rate (EER) of 0.96%. Further validation on public datasets SDU and USM, demonstrates SOTA EERs of 0.16% and 0.10%, respectively. The License for MIFVD can be accessed at: https://github.com/AHU-MedImagingIJR/MIFVD.

Prevalent lossy image compression schemes can be divided into: 1) explicit image compression (EIC), including traditional standards and neural end-to-end algorithms; 2) implicit image compression (IIC) based on implicit neural representations (INR). The former is encountering impasses of leveling off bitrate reduction at a cost of tremendous complexity while the latter suffers from excessive smoothing quality as well as lengthy decoder models. In this paper, we propose an innovative paradigm, which we dub Unicorn (Unified Neural Image Compression with One Nnumber Reconstruction). By conceptualizing the images as index-image pairs and learning the inherent distribution of pairs in a subtle neural network model, Unicorn can reconstruct a visually pleasing image from a randomly generated noise with only one index number. The neural model serves as the unified decoder of images while the noises and indexes corresponds to explicit representations. As a proof of concept, we propose an effective and efficient prototype of Unicorn based on latent diffusion models with tailored model designs. Quantitive and qualitative experimental results demonstrate that our prototype achieves significant bitrates reduction compared with EIC and IIC algorithms. More impressively, benefitting from the unified decoder, our compression ratio escalates as the quantity of images increases. We envision that more advanced model designs will endow Unicorn with greater potential in image compression. The code will be made publicly available upon publication.

Unsupervised Continuous Anomaly Detection (UCAD) is gaining attention for effectively addressing the catastrophic forgetting and heavy computational burden issues in traditional Unsupervised Anomaly Detection (UAD). However, existing UCAD approaches that rely solely on visual information are insufficient to capture the manifold of normality in complex scenes, thereby impeding further gains in anomaly detection accuracy. To overcome this limitation, we propose an unsupervised continual anomaly detection framework grounded in multimodal prompting. Specifically, we introduce a Continual Multimodal Prompt Memory Bank (CMPMB) that progressively distills and retains prototypical normal patterns from both visual and textual domains across consecutive tasks, yielding a richer representation of normality. Furthermore, we devise a Defect-Semantic-Guided Adaptive Fusion Mechanism (DSG-AFM) that integrates an Adaptive Normalization Module (ANM) with a Dynamic Fusion Strategy (DFS) to jointly enhance detection accuracy and adversarial robustness. Benchmark experiments on MVTec AD and VisA datasets show that our approach achieves state-of-the-art (SOTA) performance on image-level AUROC and pixel-level AUPR metrics.

The field weed detection task under the perspective of Plant Protection UAVs (PPU) is characterized by multi-scale targets and rich background semantic information, which belongs to the target detection task in complex scenarios. Blindly boosting the network size and overusing the attention mechanism in such tasks are not effective in improving the model accuracy. The core of the problem lies in the fact that the covariate features of the target are shifted during the transfer of the three layers of image semantic information (visual, object and conceptual layers). This phenomenon is particularly evident at the conceptual level, resulting in models that do not accurately understand the target information. Redundant semantic information and irrational attention mechanisms for complex scenarios are the cause of the problem. In this paper, we propose the Color and Feature Space Classification (CFSC) method, which aims to construct a covariate semantic information matrix that spans the visual, object and conceptual layers. Mitigating the problem of offsetting semantic information of covariate features in complex scenarios. The color and feature space classification method is applied to a one-stage detection model, YOLOv8, and experiments are conducted on three complex scene PPU weed datasets. The experimental results show that the CFSC method can improve the model accuracy, loss computation capability and accelerate the gradient descent.

Image anomaly detection usually relies on a large set of training samples and abnormal samples are relatively rare and challenging to obtain in daily industrial scenarios. In the scenario of Few-Shot Anomaly Detection (FSAD), how to better utilize the fine-grained features of the few images is a key issue. To solve these problems, a Finer-Grained Siamese Network (FGSNet) is proposed in this paper. FGSNet considers the setting of Few-Shot Anomaly Detection (FSAD) and consists of two stages. The first stage is responsible for extracting finer-grained features and roughly aligning the image features, while incorporating an efficient Fine-grained Feature Fusion Module$(\mathbf{F}^{3}\mathbf{M})$to enhance feature representation. Meanwhile, we design a Deep-supervised Loss to improve the level of fine-grained information extraction. The second is primarily used to refine and denoise the fused features, followed by detailed alignment operations for subsequent feature distribution modeling. Compared to most existing FASD models that use single-class training and single-model evaluation, FGSNet is more suitable for existing industrial scenarios. Extensive experiments are conducted on the publicly available MVTec AD and MPDD datasets in this paper. The results show that, for 2, 4 and 8-shot cases, FGSNet can increase the average Image-AUROC on MVTec AD by 0.87%, 1.27% and 1.33% respectively, compared to RegAD.

In industrial manufacturing, visual anomaly detection is critical for maintaining product quality by detecting and preventing production anomalies. Anomaly detection methods based on knowledge distillation demonstrate promising performance in addressing the unpredictability and diversity of anomalies. However, they suffer from a lack of effective guidance from anomaly-free priors when handling anomalous features and underutilize multi-scale features during the segmentation scoring stage, yielding suboptimal detection results. To alleviate these issues, we propose an Anomaly-free Prior Guided knowledge distillation (APG) for industrial anomaly detection. Firstly, it filters the abnormal features by training the de-noising target network with knowledge distillation structure. Concurrently, we propose the Prior Perception Propagation Module (P3M), which extracts more efficient anomaly-free features by imposing constraints on anomalous features. Secondly, we propose the Multi-scale Prior Guided Fusion Module (MPGFM) to improve anomaly detection accuracy by utilizing anomaly-free features from the target network as priors to guide the generation and fusion of cross-scale differential features. Finally, the Global Perception Enhancement Module (GPEM) is proposed to construct an anomaly scoring network, leveraging comprehensive scene features to enhance the detection and localization performance of numerous small-target anomalies in industrial manufacturing. Extensive experiments on the MVTecAD and BTAD datasets show that the proposed method demonstrates a consistent and significant outperformance against competing methods.

In the field of industrial production, anomaly detection is crucial for ensuring product quality and maintaining production efficiency. With the continuous advancement of computer vision technology, it has shown tremendous potential in industrial applications. However, the scarcity of labeled anomaly samples in real-world operating environments poses significant challenges for traditional anomaly detection techniques. To address this, we propose MemADet, a novel anomaly detection model that employs an unsupervised approach and leverages a representative memory bank. It employs a dynamic decision mechanism to control the representativeness of the features stored in the memory bank, and employs a weighted anomaly score calculation mechanism to further enhance the performance of image anomaly detection. Our evaluations indicate that MemADet performs robustly in industrial image anomaly detection across three datasets, with particularly no-table detection accuracy on the MVTec AD dataset. Its efficacy is further validated by competitive results on two additional datasets, highlighting its consistent and effective performance in various settings.

Applications in Engineering: In industry, surface defect detection is crucial for improving product quality . However, there are many challenges in industrial inspection scenarios, such as interference from background noise, complex small-target problems, significant variations in target objects, and the problem of finding a balance between inspection speed and accuracy. To address the above problems, this paper proposes an industrial defect-aware network based on cross-layer semantic information guidance and contextual attention enhancement (IDP-Net). Specifically, IDP-Net has four different new features. The contribution of artificial intelligence : Firstly, to solve the industrial surface context and defect similarity problem, this paper proposes a Lightweight Local Global Feature Extraction Network (LLG-Net), unlike other methods, the effective combination of self-attention blocks and convolution blocks ensures gradual integration of global and local features across multiple layers, to improve the detection ability of targets with significant changes in scale, this paper designs a Multiscale Perceptual Feature Aggregation Network (MPA-Net), adequately fuses the shallow fine-grained information and the deep semantic information. Then, to enhance the connection between multi-scale semantic information, an adaptive cross-layer feature fusion module (ACFF) is proposed, which is novel in integrating the characteristics of multiple adjacent levels to help the model better capture the different scale characterisation of the target. Finally, a Region Attention Module (RAM) is proposed and introduced in the detector to enhance the attention to the critical regions around the target object. In particular, this paper proposes a new localisation loss function (MEIoU) that enhances the network’s attention to objects at different scales. The experimental results show that 94.3%, 98.7% and 99.5% of [email protected] are obtained on steel, PCB and aluminium surface defect datasets, respectively, and 50 FPS is achieved, which is better than the current mainstream detectors and meets the demand of practical industrial production.

With the rapid development of industrial automation, large-scale production of automated pipelines has become a trend. In the production process of industrial products, the quality detection of industrial products is an essential means to avoid economic losses and ensure personal safety. Improving industrial product quality detection accuracy and speed has been an important research topic in this field. In recent years, one-stage and two-stage deep learning object detection methods have been applied in defect detection. However, problems such as significant changes in object scale, high similarity, and the balance of speed and accuracy in industrial detection scenarios result in poor performance of common object detection algorithms. To address these issues, this paper proposes a Glass Bottle Bottom Mold Sequence Recognition Data Set and designs a novel dual collaborative paths feature network (DCP- Net) for industrial defect detection. The DCP-Net is designed to extract object features with varied scales from two branches, which can effectively focus on multi-scale industrial product defect features. Moreover, this paper presents the feature filter to obtain fine-grained information about objects, significantly improving similar objects' classification. In the experiments of the open data set of steel defects and the point sequence data set of glass bottle bottom mold collected in this paper, this method achieves higher accuracy than other methods.

The detection of defects in printed circuit boards requires high accuracy and realtime performance. Existing industrial detection models generally adopt a pure convolutional structure for ease of deployment. However, the detection accuracy of these models is often insufficient to meet the requirements of the scene. To improve the detection model accuracy and ease of deployment, this paper proposes a convolutional merging Transformer network(CMTRNet). The CMTR-Net model proposes a backbone network (CNN-Former) that uses convolutional modules to replace self-attention, combining the Transformer architecture with a convolutional structure. This approach not only avoids the drawback of self-attention high computation complexity that is detrimental to deployment but also improves the model detection accuracy. Based on CNN-Former, this paper also proposes a feature fusion module that can better fuse the features extracted by CNN-Former. Further-more, based on the CMTRNet model and the characteristics of circuit board defects, this paper proposes a loss function called Melt-IoU, which can make the initial training phase smoother and further improve detection accuracy. Experiments have shown that CMTRNet outperforms existing advanced models on both datasets.