VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer
This work addresses the problem of detecting anomalies without prior examples for a broad range of applications, including industrial inspection and medical diagnosis, by offering a language-free alternative to current VLM-dependent methods.
This paper introduces VisualAD, a novel framework for zero-shot anomaly detection that operates without language models. It achieves state-of-the-art performance across 13 industrial and medical benchmarks by using learnable tokens within a Vision Transformer to encode normality and abnormality, along with spatial-aware cross-attention and a self-alignment function.
Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-text similarities for open-set discrimination. While effective, this paradigm depends on a text encoder and cross-modal alignment, which can lead to training instability and parameter redundancy. This work revisits the necessity of the text branch in ZSAD and presents VisualAD, a purely visual framework built on Vision Transformers. We introduce two learnable tokens within a frozen backbone to directly encode normality and abnormality. Through multi-layer self-attention, these tokens interact with patch tokens, gradually acquiring high-level notions of normality and anomaly while guiding patches to highlight anomaly-related cues. Additionally, we incorporate a Spatial-Aware Cross-Attention (SCA) module and a lightweight Self-Alignment Function (SAF): SCA injects fine-grained spatial information into the tokens, and SAF recalibrates patch features before anomaly scoring. VisualAD achieves state-of-the-art performance on 13 zero-shot anomaly detection benchmarks spanning industrial and medical domains, and adapts seamlessly to pretrained vision backbones such as the CLIP image encoder and DINOv2. Code: https://github.com/7HHHHH/VisualAD