DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection
By: Amirhossein Khadivi Noghredeh , Abdollah Safari , Fatemeh Ziaeetabar and more
Potential Business Impact:
Finds tiny flaws in factory products using smart learning.
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.
Similar Papers
RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection
CV and Pattern Recognition
Finds hidden flaws in factory goods faster.
Semi-Supervised Anomaly Detection in Brain MRI Using a Domain-Agnostic Deep Reinforcement Learning Approach
CV and Pattern Recognition
Spots brain anomalies in MRI scans accurately with few examples
Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection
CV and Pattern Recognition
Finds hidden problems in factory machines.