Search Results for author: Zehua Cheng

Found 8 papers, 1 papers with code

Symphony Generation with Permutation Invariant Language Model

1 code implementation10 May 2022 Jiafeng Liu, Yuanliang Dong, Zehua Cheng, Xinran Zhang, Xiaobing Li, Feng Yu, Maosong Sun

In this work, we propose a permutation invariant language model, SymphonyNet, as a solution for symbolic symphony music generation.

Audio Generation Language Modelling +2

Distributed Low Precision Training Without Mixed Precision

no code implementations18 Nov 2019 Zehua Cheng, Weiyang Wang, Yan Pan, Thomas Lukasiewicz

However, most low precision training solution is based on a mixed precision strategy.

Model Compression

Segmentation is All You Need

no code implementations30 Apr 2019 Zehua Cheng, Yuxiang Wu, Zhenghua Xu, Thomas Lukasiewicz, Weiyang Wang

Region proposal mechanisms are essential for existing deep learning approaches to object detection in images.

Face Detection Head Detection +5

FoxNet: A Multi-face Alignment Method

no code implementations22 Apr 2019 Yuxiang Wu, Zehua Cheng, Bin Huang, Yiming Chen, Xinghui Zhu, Weiyang Wang

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, face tracking, and face animation.

Clustering Face Alignment +1

Learning with Collaborative Neural Network Group by Reflection

no code implementations8 Jan 2019 Liyao Gao, Zehua Cheng

CNNG is a progression of neural systems that work cooperatively to deal with various errands independently in a similar learning framework.

Bandwidth Reduction using Importance Weighted Pruning on Ring AllReduce

no code implementations6 Jan 2019 Zehua Cheng, Zhenghua Xu

In order to save more communication bandwidth and preserve the accuracy on ring structure, which break the restrict as the node increase, we propose a new algorithm to measure the importance of gradients on large-scale cluster implementing ring all-reduce based on the size of the ratio of parameter calculation gradient to parameter value.

Cannot find the paper you are looking for? You can Submit a new open access paper.