AI RESEARCH

Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks

arXiv CS.CV

ArXi:2604.11162v1 Announce Type: new Accurate defect segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding boxes into pseudo-masks using foundation segmentation models such as the Segment Anything Model (SAM). However, these pseudo-labels are systematically noisy on industrial surfaces, often hallucinating background structure while missing sparse defects.