提出新对比学习方法，让正常样本更紧凑、异常更分离，无需标签也能精准检测异常。
Contrastive Representation Modeling for Anomaly Detection
- 重新定义正负样本关系，提升正常样本聚类和异常分离能力。
- 在工业级数据集上收敛更快，性能超越现有对比学习方法。
- 适用于无标签场景，尤其适合检测局部异常的工业质检任务。
基于距离的异常检测依赖于紧凑的正常样本嵌入，使其与异常样本充分分离。然而，传统对比学习常导致正常样本方差过大或无法保持异常样本多样性。本文分析了异常检测中的表征学习挑战，提出三种关键预训练目标：（1）正常样本紧凑聚类，（2）正常与异常强分离，（3）保留合成异常样本的多样性。基于此，我们设计一种结构化对比目标，在无需显式异常标签的情况下实现上述特性。进一步引入基于补丁的学习与评估策略，专门提升工业场景中局部异常的检测能力。实验表明，该方法收敛速度显著加快，性能优于标准对比学习，在语义与工业基准上达到或超过现有方法，包括依赖判别训练或标注异常的方法。
原文摘要 · Abstract (English)
Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting excessive variance among inliers or failing to preserve the diversity of outliers. We begin by analyzing the challenges of representation learning for anomaly detection and identify three essential properties for the pretext task: (1) compact clustering of inliers, (2) strong separation between inliers and anomalies, and (3) preservation of diversity among synthetic outliers. Building on this, we propose a structured contrastive objective that redefines positive and negative relationships during training, promoting these properties without requiring explicit anomaly labels. We extend this framework with a patch-based learning and evaluation strategy specifically designed to improve the detection of localized anomalies in industrial settings. Our approach demonstrates significantly faster convergence and improved performance compared to standard contrastive methods. It matches or surpasses anomaly detection methods on both semantic and industrial benchmarks, including methods that rely on discriminative training or explicit anomaly labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。