无需标签即可检测图像异常，通过文本库自动挖掘正类概念。
ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora
- 从大规模文本中挖掘正类概念，不依赖预设标签
- 在多种CLIP模型上实现顶尖的异常检测性能
- 对分布偏移具有强鲁棒性，适合真实场景应用
大规模视觉异常检测近年得益于如CLIP等视觉语言模型取得显著进展。然而，现有方法严重依赖预定义的、分布内（ID）的真实标签名称（正例），这些标签可能在规模上不可用、不可靠，或部署后因分布变化而过时。为实现真正的无监督异常检测，本文利用广泛可用的文本语料库进行正类标签挖掘，摆脱对正例的依赖。提出一种名为ClusterMine的新方法，在通用概念挖掘框架下，结合仅视觉样本的一致性（通过聚类）与零样本图文一致性，从大型文本语料库中提取正类概念。实验表明，ClusterMine是首个无需正例标签即达当前最优性能的方法，在多种CLIP模型上具备良好可扩展性，并对协变量分布内偏移表现出卓越鲁棒性。代码已开源：https://github.com/HHU-MMBS/clustermine_wacv_official。
原文摘要 · Abstract (English)
Large-scale visual out-of-distribution (OOD) detection has witnessed remarkable progress by leveraging vision-language models such as CLIP. However, a significant limitation of current methods is their reliance on a pre-defined set of in-distribution (ID) ground-truth label names (positives). These fixed label names can be unavailable, unreliable at scale, or become less relevant due to in-distribution shifts after deployment. Towards truly unsupervised OOD detection, we utilize widely available text corpora for positive label mining, bypassing the need for positives. In this paper, we utilize widely available text corpora for positive label mining under a general concept mining paradigm. Within this framework, we propose ClusterMine, a novel positive label mining method. ClusterMine is the first method to achieve state-of-the-art OOD detection performance without access to positive labels. It extracts positive concepts from a large text corpus by combining visual-only sample consistency (via clustering) and zero-shot image-text consistency. Our experimental study reveals that ClusterMine is scalable across a plethora of CLIP models and achieves state-of-the-art robustness to covariate in-distribution shifts. The code is available at https://github.com/HHU-MMBS/clustermine_wacv_official.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。