AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples
This work addresses the problem of detecting anomalies in limited-data scenarios for applications like industrial inspection, though it is incremental as it builds on existing prompt learning approaches.
The paper tackles few-shot anomaly detection with only normal samples by introducing AnoPLe, a multi-modal prompt learning method that simulates anomalies and uses bidirectional coupling of textual and visual prompts, achieving 94.1% and 86.2% Image AUROC on MVTec-AD and VisA datasets, respectively, with a gap of about 1% from state-of-the-art methods.
Few-shot Anomaly Detection (FAD) poses significant challenges due to the limited availability of training samples and the frequent absence of abnormal samples. Previous approaches often rely on annotations or true abnormal samples to improve detection, but such textual or visual cues are not always accessible. To address this, we introduce AnoPLe, a multi-modal prompt learning method designed for anomaly detection without prior knowledge of anomalies. AnoPLe simulates anomalies and employs bidirectional coupling of textual and visual prompts to facilitate deep interaction between the two modalities. Additionally, we integrate a lightweight decoder with a learnable multi-view signal, trained on multi-scale images to enhance local semantic comprehension. To further improve performance, we align global and local semantics, enriching the image-level understanding of anomalies. The experimental results demonstrate that AnoPLe achieves strong FAD performance, recording 94.1% and 86.2% Image AUROC on MVTec-AD and VisA respectively, with only around a 1% gap compared to the SoTA, despite not being exposed to true anomalies. Code is available at https://github.com/YoojLee/AnoPLe.