用强化学习选关键图像块，用少量标注数据提升缺陷检测精度。
DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection
- 用强化学习动态选择最有价值的图像块进行训练
- 在MVTec AD上F1_max提升0.15，最高达0.37
- 适合标注数据稀缺的工业缺陷检测场景
工业视觉检测中的异常检测因缺陷样本稀少而困难。现有方法多依赖仅含正常数据的无监督重建，常导致过拟合且难以发现细微缺陷。本文提出一种半监督深度强化学习框架，集成神经批采样器、自编码器和预测器。基于强化学习的采样器通过复合奖励机制，在探索与利用间平衡，自适应选择信息量高的图像块；自编码器生成损失图以突出异常区域，预测器在损失图空间中执行分割。这种交互使系统能在少量标注数据下有效学习正常与缺陷模式。在MVTec AD数据集上的实验表明，该方法在准确率和细微缺陷定位上优于最新方法，平均提升F1_max 0.15、AUC 0.06，最佳情况下F1_max提升达0.37，同时保持低计算复杂度。
原文摘要 · Abstract (English)
Anomaly detection in industrial visual inspection is challenging due to the scarcity of defective samples. Most existing methods rely on unsupervised reconstruction using only normal data, often resulting in overfitting and poor detection of subtle defects. We propose a semi-supervised deep reinforcement learning framework that integrates a neural batch sampler, an autoencoder, and a predictor. The RL-based sampler adaptively selects informative patches by balancing exploration and exploitation through a composite reward. The autoencoder generates loss profiles highlighting abnormal regions, while the predictor performs segmentation in the loss-profile space. This interaction enables the system to effectively learn both normal and defective patterns with limited labeled data. Experiments on the MVTec AD dataset demonstrate that our method achieves higher accuracy and better localization of subtle anomalies than recent state-of-the-art approaches while maintaining low complexity, yielding an average improvement of 0.15 in F1_max and 0.06 in AUC, with a maximum gain of 0.37 in F1_max in the best case.
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。