SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect Paper • 2505.19750 • Published May 26 • 2
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16 • 109
nvidia/segformer-b0-finetuned-cityscapes-1024-1024 Image Segmentation • Updated Aug 8, 2022 • 6.97k • • 10