51 citations · 79 across the 5 of their papers we have counts for
7 papers
Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
Yimeng Zhang, Akshay Karkal Kamath, Qiucheng Wu +6
In this paper, we propose a data-model-hardware tri-design framework for high-throughput, low-cost, and high-accuracy multi-object tracking (MOT) on High-Definition (HD) video stre…
Auto-scaling Vision Transformers without Training
Wuyang Chen, Wei Huang, Xianzhi Du +3
This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for desig…
Font Completion and Manipulation by Cycling Between Multi-Modality Representations
Ye Yuan, Wuyang Chen, Zhaowen Wang +4
Generating font glyphs of consistent style from one or a few reference glyphs, i.e., font completion, is an important task in topographical design. As the problem is more well-defi…
Contrastive Syn-to-Real Generalization
Wuyang Chen, Zhiding Yu, Shalini De Mello +4
Training on synthetic data can be beneficial for label or data-scarce scenarios. However, synthetically trained models often suffer from poor generalization in real domains due to…
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
Wuyang Chen, Xinyu Gong, Zhangyang Wang
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intens…
Learning to Optimize: A Primer and A Benchmark
Tianlong Chen, Xiaohan Chen, Wuyang Chen +4
Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods, aiming at reducing the laborious iterations of hand engineering.…