14 papers
Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection
Sara Abdulaziz, Abdulrahman Al-Abri, Giacomo D'Amicantonio +1
Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal supervision and fine-grained spati…
Auditing Frame-Level AUC in Weakly Supervised Video Anomaly Detection: Granularity, Resolution, and Scene Bias
Sara Abdulaziz, Egor Bondarev
Frame-level area under the ROC curve (AUC) is the dominant evaluation metric for weakly supervised video anomaly detection (WSVAD). Its standard form measures whether an anomalous…
ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection
Camile Lendering, Erkut Akdag, JoaquÃn Figueira +1
Unified anomaly detection requires modeling highly heterogeneous normal data without access to anomalous samples. While foundation models like DINOv2 provide rich token representat…
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
Camile Lendering, Erkut Akdag, Egor Bondarev
Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achieve strong results employing fou…
AOI-SSL: Self-Supervised Framework for Efficient Segmentation of Wire-bonded Semiconductors In Optical Inspection
JoaquÃn Figueira, Rob Van Gastel, Giacomo D'Amicantonio +4
Segmentation models in automated optical inspection of wire-bonded semiconductors are typically device-specific and must be re-trained when new devices or distribution shifts appea…
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Camile Lendering, Erkut Akdag, Egor Bondarev
Accurate defect segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding b…