ViP$^2$-CLIP: Visual-Perception Prompting with Unified Alignment for Zero-Shot Anomaly Detection
This addresses the problem of detecting anomalies without training data for industrial and medical applications, offering a novel approach that improves over existing CLIP-based methods.
The paper tackles zero-shot anomaly detection by introducing ViP^2-CLIP, which uses a Visual-Perception Prompting mechanism to generate fine-grained textual prompts without manual templates or class-name priors, achieving state-of-the-art performance on 15 benchmarks.
Zero-shot anomaly detection (ZSAD) aims to detect anomalies without any target domain training samples, relying solely on external auxiliary data. Existing CLIP-based methods attempt to activate the model's ZSAD potential via handcrafted or static learnable prompts. The former incur high engineering costs and limited semantic coverage, whereas the latter apply identical descriptions across diverse anomaly types, thus fail to adapt to complex variations. Furthermore, since CLIP is originally pretrained on large-scale classification tasks, its anomaly segmentation quality is highly sensitive to the exact wording of class names, severely constraining prompting strategies that depend on class labels. To address these challenges, we introduce ViP$^{2}$-CLIP. The key insight of ViP$^{2}$-CLIP is a Visual-Perception Prompting (ViP-Prompt) mechanism, which fuses global and multi-scale local visual context to adaptively generate fine-grained textual prompts, eliminating manual templates and class-name priors. This design enables our model to focus on precise abnormal regions, making it particularly valuable when category labels are ambiguous or privacy-constrained. Extensive experiments on 15 industrial and medical benchmarks demonstrate that ViP$^{2}$-CLIP achieves state-of-the-art performance and robust cross-domain generalization.