Cong Hao

most citedM

^{3}

ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

33 citations · 37 across the 3 of their papers we have counts for

collaborators

Showing cs.CVShow all

2 papers · 1 filter

cs.CV2022★ 33 cited

M $^{3}$ ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Hanxue Liang, Zhiwen Fan, Rishov Sarkar +6

Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world s…

cs.CV2022★ 3 cited

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…

M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices

M $^{3}$ ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design