AI RESEARCH
TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection
arXiv CS.CV
•
ArXi:2603.16451v1 Announce Type: new Anomaly detection plays a key role in industrial quality control, where defects must be identified despite the scarcity of labeled faulty samples. Recent self-supervised approaches, such as GLASS, learn normal visual patterns using only defect-free data and have shown strong performance on industrial benchmarks. However, their computational requirements limit deployment on resource-constrained edge platforms. In addition to evaluating performance on the MVTec-AD benchmark, we investigate robustness to contaminated