most citedSegmentation is All You Need

15 citations · 28 across the 6 of their papers we have counts for

collaborators

6 papers

eess.IV2022

Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report

Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang +50

Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While num…

cs.CV20193 cited

Distributed Low Precision Training Without Mixed Precision

Zehua Cheng, Weiyang Wang, Yan Pan +1

Low precision training is one of the most popular strategies for deploying the deep model on limited hardware resources. Fixed point implementation of DCNs has the potential to all…

cs.CV201915 cited

Segmentation is All You Need

Zehua Cheng, Yuxiang Wu, Zhenghua Xu +2

Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under…

cs.CV20191 cited

FoxNet: A Multi-face Alignment Method

Yuxiang Wu, Zehua Cheng, Bin Huang +3

Multi-face alignment aims to identify geometry structures of multiple faces in an image, and its performance is essential for the many practical tasks, such as face recognition, fa…

cs.LG20191 cited

Learning with Collaborative Neural Network Group by Reflection

Liyao Gao, Zehua Cheng

For the present engineering of neural systems, the preparing of extensive scale learning undertakings generally not just requires a huge neural system with a mind boggling preparin…

cs.LG20198 cited

Bandwidth Reduction using Importance Weighted Pruning on Ring AllReduce

Zehua Cheng, Zhenghua Xu

It is inevitable to train large deep learning models on a large-scale cluster equipped with accelerators system. Deep gradient compression would highly increase the bandwidth utili…