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