activity
20172022
most citedMind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search

97 citations · 296 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2021

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…

cs.CV2021

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…

cs.CV2020

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…

cs.CV20206 cited

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…

cs.CV202029 cited

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…

cs.CV202013 cited

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…