2 papers
cs.CV2024
Relative Difficulty Distillation for Semantic Segmentation
Dong Liang, Yue Sun, Yun Du +2
Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student net…
cs.CV2024
PIE: Physics-inspired Low-light Enhancement
Dong Liang, Zhengyan Xu, Ling Li +2
In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem o…