3 papers
cs.CV2025
WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining
Haoran Wang, Lian Huai, Wenbin Li +3
We have witnessed remarkable progress in foundation models in vision tasks. Currently, several recent works have utilized the segmenting anything model (SAM) to boost the segmentat…
eess.IV2025
CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image
Xiaojun Tang, Jingru Wang, Guangwei Huang +5
Recent advancements in Blind Image Restoration (BIR) methods, based on Generative Adversarial Networks and Diffusion Models, have significantly improved visual quality. However, th…
cs.CV2023
Decoupled DETR For Few-shot Object Detection
Zeyu Shangguan, Lian Huai, Tong Liu +1
Few-shot object detection (FSOD), an efficient method for addressing the severe data-hungry problem, has been extensively discussed. Current works have significantly advanced the p…