3 papers
cs.CV2026
AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
Matic FuÄka, Vitjan Zavrtanik, Danijel SkoÄaj
Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent approaches leverage vision-langu…
cs.CV2025
SALAD -- Semantics-Aware Logical Anomaly Detection
Matic FuÄka, Vitjan Zavrtanik, Danijel SkoÄaj
Recent surface anomaly detection methods excel at identifying structural anomalies, such as dents and scratches, but struggle with logical anomalies, such as irregular or missing o…
cs.CV2024
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Jer Pelhan, Alan LukežiÄ, Vitjan Zavrtanik +1
Low-shot object counters estimate the number of objects in an image using few or no annotated exemplars. Objects are localized by matching them to prototypes, which are constructed…