Beyond Normal References: Discriminative Few-Shot Anomaly Detection

• URL: http://arxiv.org/abs/2605.23231v1
• Date: Fri, 22 May 2026 04:48:14 GMT
• Title: Beyond Normal References: Discriminative Few-Shot Anomaly Detection
• Abstract summary: This paper considers a practical few-shot anomaly detection setting, termed discriminative FSAD.<n>Existing FSAD methods rely on normal-only references through normality matching.<n>We introduce an intrinsic deviation learning framework that leverages both reference types.
• Score: 35.05951359908686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 FSAD methods rely on normal-only references through normality matching, ignoring the discriminative clues in anomalous references, while directly fitting both references can overfit to the seen anomalies. We introduce IDEAL, an intrinsic deviation learning framework that leverages both reference types to learn intrinsic deviation patterns characterizing generalizable abnormality as deviations from normality. IDEAL decomposes the learning process into two novel components: 1) a Normal Variation Eraser to suppress nuisance normal variations that may lead to noisy deviations from normality, thereby highlighting anomaly-relevant deviation representations; 2) an Intrinsic Deviation Encoder to decompose these denoised deviation representations into intrinsic deviation vectors capturing the most discriminative orthogonal deviation directions. At inference, IDEAL scores query-to-normal deviations preserved after projection onto the learned intrinsic deviation vectors, enabling generalization for both seen and unseen anomalies. Extensive experiments on eight real-world datasets show that IDEAL generalizes effectively to unseen anomalies and consistently outperforms existing state-of-the-art FSAD methods. Code and data will be available at \href{https://github.com/mala-lab/IDEAL}{https://github.com/mala-lab/IDEAL}.

Related papers

• DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation [52.52576712810738]
  Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically provide only normal images, making anomaly samples difficult to collect.<n>Existing methods mainly rely on texture images or text descriptions as anomaly sources, which often produce unrealistic anomalies.<n>We propose anomaly transfer-based zero-shot generation, which reuses real anomalies from existing source products.
  arXiv  Detail & Related papers  (2026-09-02T04:03:05Z)
• Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference [54.774686416991386]
  We argue that multimodal anomaly detection should be reframed as a cross-modal contextual inference problem.<n>This perspective has implications for model design, evaluation protocols, and benchmark construction.
  arXiv  Detail & Related papers  (2026-04-14T19:32:55Z)
• Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision [31.57563937222115]
  Dynamic graph anomaly detection (DGAD) is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies.<n>We propose an effective, generalizable, and model-agnostic framework with three main components.
  arXiv  Detail & Related papers  (2026-02-23T16:25:35Z)
• CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection [34.133298397463754]
  Centre-Enhanced Discriminative Learning (CEDL) is a novel supervised anomaly detection framework.<n>It embeds geometric normality directly into the discriminative objective.<n>CEDL achieves competitive and balanced performance across diverse real-world anomaly detection tasks.
  arXiv  Detail & Related papers  (2025-11-15T23:44:18Z)
• Normal-Abnormal Guided Generalist Anomaly Detection [24.763955488489852]
  Generalist Anomaly Detection (GAD) aims to train a unified model on an original domain that can detect anomalies in new target domains.<n>Previous GAD methods primarily use only normal samples as references, overlooking the valuable information contained in anomalous samples that are often available in real-world scenarios.<n>We propose normal-abnormal-guided generalist anomaly detection, which leverages both normal and anomalous samples as references to guide anomaly detection across diverse domains.
  arXiv  Detail & Related papers  (2025-10-01T04:27:10Z)
• KKA: Improving Vision Anomaly Detection through Anomaly-related Knowledge from Large Language Models [54.63075553088399]
  Key Knowledge Augmentation (KKA) is a method that extracts anomaly-related knowledge from large language models (LLMs)<n>KKA classifies the generated anomalies as easy anomalies and hard anomalies according to their similarity to normal samples.<n> Experimental results show that the proposed method significantly improves the performance of various vision anomaly detectors.
  arXiv  Detail & Related papers  (2025-02-14T07:46:49Z)
• GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
  Diffusion models tend to reconstruct normal counterparts of test images with certain noises added. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2024-06-11T17:27:23Z)
• Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection [26.08881235151695]
  Open-set supervised anomaly detection (OSAD) aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies. We introduce a novel approach, namely Anomaly Heterogeneity Learning (AHL), that simulates a diverse set of heterogeneous anomaly distributions. We show that AHL can 1) substantially enhance different state-of-the-art OSAD models in detecting seen and unseen anomalies, and 2) effectively generalize to unseen anomalies in new domains.
  arXiv  Detail & Related papers  (2023-10-19T14:47:11Z)
• Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection [14.27685411466415]
  Most anomaly detection (AD) models are learned using only normal samples in an unsupervised way. We propose a novel explicit boundary guided semi-push-pull contrastive learning mechanism.
  arXiv  Detail & Related papers  (2022-07-04T14:50:23Z)
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
  We introduce a novel weakly-supervised anomaly detection framework to train detection models. The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability. Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
  arXiv  Detail & Related papers  (2021-08-01T14:33:17Z)
• Deep Weakly-supervised Anomaly Detection [118.55172352231381]
  Pairwise Relation prediction Network (PReNet) learns pairwise relation features and anomaly scores. PReNet can detect any seen/unseen abnormalities that fit the learned pairwise abnormal patterns. Empirical results on 12 real-world datasets show that PReNet significantly outperforms nine competing methods in detecting seen and unseen anomalies.
  arXiv  Detail & Related papers  (2019-10-30T00:40:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.