97 citations · 296 across the 17 of their papers we have counts for
8 papers · 1 filter
Vision Transformers with Patch Diversification
Chengyue Gong, Dilin Wang, Meng Li +2
Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optima…
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Dilin Wang, Chengyue Gong, Meng Li +2
Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles a…
EVRNet: Efficient Video Restoration on Edge Devices
Sachin Mehta, Amit Kumar, Fitsum Reda +4
Video transmission applications (e.g., conferencing) are gaining momentum, especially in times of global health pandemic. Video signals are transmitted over lossy channels, resulti…
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
Hsin-Pai Cheng, Feng Liang, Meng Li +5
Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neur…
Can Temporal Information Help with Contrastive Self-Supervised Learning?
Yutong Bai, Haoqi Fan, Ishan Misra +6
Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent…
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Chengyue Gong, Dilin Wang, Meng Li +2
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy aug…