NexViTAD：基于视觉基础模型与多任务学习的少样本无监督跨域缺陷检测
NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning
AI总结：
提出基于视觉基础模型的少样本跨域异常检测框架NexViTAD，通过分层适配器、共享子空间投影、多任务解码器和Sinkhorn-K-means聚类推理，在MVTec AD上实现SOTA跨域缺陷检测性能。
摘要：
本文提出了一种基于视觉基础模型的少样本跨域异常检测框架Nexus Vision Transformer for Anomaly Detection (NexViTAD)，通过创新的共享子空间投影机制和多任务学习（MTL）模块有效解决了工业异常检测中的域偏移挑战。主要创新包括：(1) 分层适配器模块，自适应融合Hiera和DINO-v2预训练模型的互补特征，构建更鲁棒的特征表示；(2) 共享子空间投影策略，通过瓶颈维度约束和跳跃连接机制实现有效的跨域知识迁移；(3) MTL Decoder架构支持多个源域同时处理，显著增强模型泛化能力；(4) 基于Sinkhorn-K-means聚类的异常分数推理方法，结合高斯滤波和自适应阈值处理实现精确像素级检测。在MVTec AD数据集上评估，NexViTAD达到最先进性能，目标域AUC为97.5%、AP为70.4%、PRO为95.2%，超越其他近期模型，标志着跨域缺陷检测的变革性进展。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
