NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning
This paper presents a novel few-shot cross-domain anomaly detection framework, Nexus Vision Transformer for Anomaly Detection (NexViTAD), based on vision foundation models, which effectively addresses domain-shift challenges in industrial anomaly detection through innovative shared subspace projection mechanisms and multi-task learning (MTL) module. The main innovations include: (1) a hierarchical adapter module that adaptively fuses complementary features from Hiera and DINO-v2 pre-trained models, constructing more robust feature representations; (2) a shared subspace projection strategy that enables effective cross-domain knowledge transfer through bottleneck dimension constraints and skip connection mechanisms; (3) a MTL Decoder architecture supports simultaneous processing of multiple source domains, significantly enhancing model generalization capabilities; (4) an anomaly score inference method based on Sinkhorn-K-means clustering, combined with Gaussian filtering and adaptive threshold processing for precise pixel level. Valuated on the MVTec AD dataset, NexViTAD delivers state-of-the-art performance with an AUC of 97.5%, AP of 70.4%, and PRO of 95.2% in the target domains, surpassing other recent models, marking a transformative advance in cross-domain defect detection.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Task LearningAnomaly DetectionResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #82 | Anomaly Detection | MVTec AD | NexViTAD | Detection AUROC: 97.5 |
Similar Papers 제목 키워드 기반
Accelerating New Product Introduction for Visual Quality Inspection via Few-Shot Diffusion-Based Defect Synthesis
Industrial visual inspection systems often suffer from a severe scarcity of labeled defect data, particularly during the early stages of New Product Introduction (NPI). This limitation hinders the deployment of robust su…
Representation LearningData AugmentationDomain AdaptationCausal Language Model for Zero-shot Constrained Keyphrase Generation
Recently, most of the state-of-the-art keyphrase prediction models are based on a supervised generative model.Although it shows noticeable improvement over statistical methods, it still struggles with low performance on …
Keyphrase GenerationLanguage ModelingLanguage ModellingAutoregressive Language Model for Zero-shot Constrained Keyphrase Generation
Recently, most of the state-of-the-art keyphrase prediction models are based on a supervised generative model. It shows significantly better than before. Nevertheless, it still faces domain robustness and building datase…
Keyphrase GenerationLanguage ModelingLanguage ModellingUnsupervised Defect Detection for Surgical Instruments
Ensuring the safety of surgical instruments requires reliable detection of visual defects. However, manual inspection is prone to error, and existing automated defect detection methods, typically trained on natural/indus…
Domain AdaptationA One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspection
Visual surface inspection is a challenging task owing to the highly diverse appearance of target surfaces and defective regions. Previous attempts heavily rely on vast quantities of training examples with manual annotati…
Generative Adversarial Network