Weakly Supervised Defect Localization with Residual Features

We address the task of weakly supervised defect localization using image-level labels, which is essential for visual inspections in industrial manufacturing and infrastructure maintenance. Existing weakly supervised semantic segmentation and multiple instance learning (MIL) methods often struggle to accurately localize defects on complex structures and "in-the-wild" backgrounds. To overcome these limitations, we propose a novel MIL framework that incorporates two key innovations: residual feature learning (RFL), which highlights defect patterns by contrasting input images with reference (normal) images in the feature space, and reference image selection (RIS), which dynamically selects reference images based on similarity to enhance residual feature quality. RIS further contributes to localization performance by sampling highly similar reference images during training. We evaluate our method on the VisA and RDD2020/2022 datasets, demonstrating superior performance compared to weakly supervised semantic segmentation methods and conventional MIL-based methods in defect localization.