DevPrompt: Deviation-Based Prompt Learning for One-Normal ShotImage Anomaly Detection

2026-01-21 · Morteza Poudineh, Marc Lalonde arxiv

Few-normal shot anomaly detection (FNSAD) aims to detect abnormal regions in images using only a few normal training samples, making the task highly challenging due to limited supervision and the diversity of potential defects. Recent approaches leverage vision-language models such as CLIP with prompt-based learning to align image and text features. However, existing methods often exhibit weak discriminability between normal and abnormal prompts and lack principled scoring mechanisms for patch-level anomalies. We propose a deviation-guided prompt learning framework that integrates the semantic power of vision-language models with the statistical reliability of deviation-based scoring. Specifically, we replace fixed prompt prefixes with learnable context vectors shared across normal and abnormal prompts, while anomaly-specific suffix tokens enable class-aware alignment. To enhance separability, we introduce a deviation loss with Top-K Multiple Instance Learning (MIL), modeling patch-level features as Gaussian deviations from the normal distribution. This allows the network to assign higher anomaly scores to patches with statistically significant deviations, improving localization and interpretability. Experiments on the MVTecAD and VISA benchmarks demonstrate superior pixel-level detection performance compared to PromptAD and other baselines. Ablation studies further validate the effectiveness of learnable prompts, deviation-based scoring, and the Top-K MIL strategy.

📄 PDF Abstract BibTeX arXiv:2601.15453

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple Instance Learning Anomaly Detection

Evidential Federated Learning for Skin Lesion Image Classification

2024-11-15 · Rutger Hendrix, Federica Proietto Salanitri, Concetto Spampinato, Simone Palazzo 외

We introduce FedEvPrompt, a federated learning approach that integrates principles of evidential deep learning, prompt tuning, and knowledge distillation for distributed skin lesion classification. FedEvPrompt leverages …

Classification Federated Learning image-classification Image Classification+3

VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment

2026-06-03 · Zi Wang, Katsuya Hotta, Yawen Zou, Koichiro Kamide 외 arxiv

Few-shot cross-category 3D anomaly detection aims to determine whether an unknown point cloud belongs to a target normal category using only a few normal references. Existing training-based methods usually require catego…

3D Anomaly Detection

LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection

2026-08-19 · Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le, Trung Le 외 arxiv

Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations. Existing detectors rely on geometric or reconstruc…

Anomaly Detection Code Generation

FreqAnchorAD: Language-Free Zero-Shot Anomaly Detection via Frequency-Deviation Anchoring

2026-08-01 · Jianfeng Qiu, Peiyuan Li, Juan Xie, Xueliang Ma 외 arxiv

Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent ZSAD methods build on pretrained vision models, particularly CLIP, …

Anomaly Detection

Beyond Normal References: Discriminative Few-Shot Anomaly Detection

2026-05-22 · Huan Wang, Jun Shen, Jun Yan, Guansong Pang arxiv

This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomalous examples are available as references during inference. Existing …