61 citations · 104 across the 8 of their papers we have counts for
4 papers · 1 filter
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
Tao Yu, Cuiling Lan, Wenjun Zeng +3
Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For…
Local Patch AutoAugment with Multi-Agent Collaboration
Shiqi Lin, Tao Yu, Ruoyu Feng +3
Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieve…
GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
Simeng Sun, Tao Yu, Jiahua Xu +2
A good distortion representation is crucial for the success of deep blind image quality assessment (BIQA). However, most previous methods do not effectively model the relationship…
Learning Omni-frequency Region-adaptive Representations for Real Image Super-Resolution
Xin Li, Xin Jin, Tao Yu +4
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance…