Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenes

• URL: http://arxiv.org/abs/2602.07694v1
• Date: Sat, 07 Feb 2026 20:36:24 GMT
• Title: Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenes
• Authors: Wenping Jin, Yuyang Tang, Li Zhu,
• Abstract summary: textbfCoalAD is a benchmark for unsupervised foreign-object anomaly detection with pixel-level localization in coal-stream scenes.<n>We propose a complementary-cue collaborative perception framework that extracts and fuses complementary anomaly evidence from three perspectives.<n>Experiments on CoalAD demonstrate that our method outperforms widely used baselines across the evaluated image-level and pixel-level metrics.
• Score: 6.184948083111668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable foreign-object anomaly detection and pixel-level localization in conveyor-belt coal scenes are essential for safe and intelligent mining operations. This task is particularly challenging due to the highly unstructured environment: coal and gangue are randomly piled, backgrounds are complex and variable, and foreign objects often exhibit low contrast, deformation, occlusion, resulting in coupling with their surroundings. These characteristics weaken the stability and regularity assumptions that many anomaly detection methods rely on in structured industrial settings, leading to notable performance degradation. To support evaluation and comparison in this setting, we construct \textbf{CoalAD}, a benchmark for unsupervised foreign-object anomaly detection with pixel-level localization in coal-stream scenes. We further propose a complementary-cue collaborative perception framework that extracts and fuses complementary anomaly evidence from three perspectives: object-level semantic composition modeling, semantic-attribution-based global deviation analysis, and fine-grained texture matching. The fused outputs provide robust image-level anomaly scoring and accurate pixel-level localization. Experiments on CoalAD demonstrate that our method outperforms widely used baselines across the evaluated image-level and pixel-level metrics, and ablation studies validate the contribution of each component. The code is available at https://github.com/xjpp2016/USAD.

Related papers

• UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction [83.48950950780554]
  Building extraction from remote sensing images is a challenging task due to the complex structure variations of buildings.<n>Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models.<n>We present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet) to exploit high-quality global-local visual semantics.
  arXiv  Detail & Related papers  (2025-12-15T02:59:16Z)
• CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding [5.663297699303346]
  We introduce CogStereo, a novel framework that addresses challenging regions without relying on dataset-specific priors.<n>CogStereo embeds implicit spatial cognition into the refinement process by using monocular depth features as priors.<n>CogStereo employs a dual-conditional refinement mechanism that combines pixel-wise uncertainty with cognition-guided features for consistent global correction of mismatches.
  arXiv  Detail & Related papers  (2025-10-25T02:09:04Z)
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors [58.75916798814376]
  We develop a few-shot anomaly detector termed FoundAD.<n>We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings.<n>The simple operator acts as an effective tool for anomaly detection to characterize and identify out-of-distribution regions in an image.
  arXiv  Detail & Related papers  (2025-10-02T11:53:20Z)
• OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenes [3.0743391441996684]
  Anomaly segmentation aims to identify Out-of-Distribution (OoD) anomalous objects within images.<n>Existing pixel-wise methods typically assign anomaly scores individually and employ a global thresholding strategy to segment anomalies.<n>We introduce OoDDINO, a novel multi-level anomaly segmentation framework designed to address these limitations.
  arXiv  Detail & Related papers  (2025-07-02T08:15:11Z)
• Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments [27.72114466968709]
  Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality.<n>Existing methods are capable of detecting defects in pre-defined imaging environments.<n>We propose a novel method for anomaly detection and localization in industrial environments.<n>HetNet can learn to model the feature of normal patterns using limited information about local changes.
  arXiv  Detail & Related papers  (2025-06-19T06:08:47Z)
• Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach [69.01456182499486]
  textbfBR-Gen is a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations.<n>textbfNFA-ViT is a Noise-guided Forgery Amplification Vision Transformer that enhances the detection of localized forgeries.
  arXiv  Detail & Related papers  (2025-04-16T09:57:23Z)
• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [68.14842693208465]
  GeneralAD is an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining.
  arXiv  Detail & Related papers  (2024-07-17T09:27:41Z)
• View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesis [0.0]
  We introduce and formalize Scene Anomaly Detection (Scene AD) as the task of unsupervised, pixel-wise anomaly localization.<n>We evaluate progress in Scene AD using ToyCity, the first multi-object, multi-view real-image dataset.<n>Our experiments demonstrate that OmniAD, when used with augmented views, yields a 64.33% increase in pixel-wise (F_1) score over Reverse Distillation with no augmentation.
  arXiv  Detail & Related papers  (2024-06-26T01:54:10Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation [50.556961575275345]
  We propose a perception-aware fusion framework to promote segmentation robustness in adversarial scenes. We show that our scheme substantially enhances the robustness, with gains of 15.3% mIOU, compared with advanced competitors.
  arXiv  Detail & Related papers  (2023-08-08T01:55:44Z)
• Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization [19.23452967227186]
  We propose a novel framework for unsupervised anomaly detection and localization. Our method aims at learning dense and compact distribution from normal images with a coarse-to-fine alignment process. Our framework is effective in detecting various real-world defects and achieves a new state-of-the-art in industrial unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-10-09T10:44:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.