2 papers
eess.IV2025
UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation
Yue Li, Qing Xu, Yixuan Zhang +8
The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly de…
cs.CV2025
CoMA: Complementary Masking and Hierarchical Dynamic Multi-Window Self-Attention in a Unified Pre-training Framework
Jiaxuan Li, Qing Xu, Xiangjian He +6
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a prete…