聚焦与补充：双增强视觉Transformer用于多类异常分类
Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classification
- Huazhong University of Science and Technology（华中科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出MACO框架，通过软聚焦注意力和辅助分类标记增强视觉Transformer，结合基于相关性的数量估计，解决多类异常分类中的噪声表示和未知类别数问题，在MVTec AD和MTD数据集上显著提升性能。
AI中文摘要：
工业视觉中的多类异常分类由于异常表示的噪声/不完整性以及异常类别数量的未知性而仍然具有挑战性。为了克服这一问题，我们提出了MACO，一种新颖的多类异常分类框架，该框架学习全面的表示并在无需先验知识的情况下动态估计类别数量。首先，软聚焦注意力利用异常图集中于相关的异常区域，同时抑制背景噪声。其次，辅助分类（[A-CLS]）标记补充了[CLS]标记。它们共同关注不同的异常子区域，产生更全面和更具判别性的特征。这些[A-CLS]标记在更多任务和领域中也有效。为了推断类别数量，我们提出了基于相关性的数量估计策略。它计算标记类别之间的平均相关性，并将其可分离性线索转移到未标记集合。在MVTec AD和MTD数据集上的实验证明了我们的优越性。在已知类别数量的情况下，MACO在两个数据集上分别将ARI提高了6.5%和16.3%。在更具挑战性的未知数量场景中，它在MTD上实现了11.2%的NMI增益，并在MVTec AD上以24.1%的UPS优于现有的数量估计策略。代码将在该https URL上发布。
英文摘要：
Multi-class anomaly classification in industrial vision remains challenging due to noisy/incomplete anomaly representations and the unknown number of anomaly classes. To overcome this, we propose MACO, a novel multi-class anomaly classification framework that learns comprehensive representations and dynamically estimates class number without prior knowledge. First, a soft-focus attention uses anomaly maps to concentrate on relevant abnormal regions, while suppressing background noise. Second, auxiliary classification ([A-CLS]) tokens complement the [CLS] token. They collectively attend to diverse anomaly sub-regions, yielding more holistic and discriminative features. These [A-CLS] tokens are also effective across more tasks and domains. To infer the class number, we propose Correlation-based Number Estimation strategy. It computes the average correlation among labeled classes and transfers its separability cue to the unlabeled set. Experiments on MVTec AD and MTD datasets demonstrate our superiority. Under known class number, MACO improves ARI by 6.5% and $\textbf{16.3%}$ on both datasets, respectively. In the more challenging unknown number scenario, it achieves an $\textbf{11.2%}$ NMI gain on MTD and outperforms existing number estimation strategies by $\textbf{24.1%}$ UPS on MVTec AD. Code will be released at https://github.com/HUST-SLOW/MACO.
