2 papers
cs.CV2023
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Yuang Liu, Jing Wang, Qiang Zhou +3
Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabel…
cs.CV2023
Language-guided Few-shot Semantic Segmentation
Jing Wang, Yuang Liu, Qiang Zhou +1
Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segm…