10 papers
DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models
Dingrong Wang, Xian Tao, Zhen Qu +5
Industrial anomaly localization aims to accurately identify and localize abnormal regions in industrial products, addressing the critical challenge of detecting unseen defect categ…
AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
Zhen Qu, Xian Tao, Xiaoyi Bao +4
Large multimodal models (LMMs) exhibit strong task generalization capabilities, offering new opportunities for zero-shot visual anomaly segmentation (ZSAS). However, existing LMM-b…
DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup
Zhen Qu, Xian Tao, Xinyi Gong +7
Recent vision-language models (e.g., CLIP) have demonstrated remarkable class-generalizable ability to unseen classes in few-shot anomaly segmentation (FSAS), leveraging supervised…
CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
Qiyu Chen, Zhen Qu, Wei Luo +7
Recently, large pre-trained vision-language models have shown remarkable performance in zero-shot anomaly detection (ZSAD). With fine-tuning on a single auxiliary dataset, the mode…
Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection
Qiyu Chen, Huiyuan Luo, Haiming Yao +4
Anomaly detection plays a vital role in the inspection of industrial images. Most existing methods require separate models for each category, resulting in multiplied deployment cos…
Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection
Zhen Qu, Xian Tao, Xinyi Gong +5
Recently, vision-language models (e.g. CLIP) have demonstrated remarkable performance in zero-shot anomaly detection (ZSAD). By leveraging auxiliary data during training, these mod…
ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement
Shichen Qu, Xian Tao, Zhen Qu +3
Unsupervised anomaly localization on industrial textured images has achieved remarkable results through reconstruction-based methods, yet existing approaches based on image reconst…
VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
Zhen Qu, Xian Tao, Mukesh Prasad +4
Recently, large-scale vision-language models such as CLIP have demonstrated immense potential in zero-shot anomaly segmentation (ZSAS) task, utilizing a unified model to directly d…
Investigating Shift Equivalence of Convolutional Neural Networks in Industrial Defect Segmentation
Zhen Qu, Xian Tao, Fei Shen +2
In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consist…
The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detection
Xian Tao, Zhen Qu, Hengliang Luo +6
The Vision Challenge Track 1 for Data-Effificient Defect Detection requires competitors to instance segment 14 industrial inspection datasets in a data-defificient setting. This re…