Hao Yu

Hao Yu

Auto-generated profile, based on publicly available information

Hao Yu

Huixiang Intelligent Technology (Tianjin) Co., Ltd, Tianjin, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2024 in Neurocomputing
Verified
Journal Article
Closed access
GCGuangtao Cheng
Guangtao Cheng
XCXue Chen
Xue Chen
CWChenyi Wang
Chenyi Wang
XLXiaobo Li
Xiaobo Li
BXBaoyi Xian
Baoyi Xian
HYHao Yu
Hao Yu

1 January 2018 in IEEE Access
Verified
Journal Article
Open access
ZQZheng Qin
Zheng Qin
ZZZhaoning Zhang
Zhaoning Zhang
SZShiqing Zhang
Shiqing Zhang
HYHao Yu
Hao Yu
YPYuxing Peng
Yuxing Peng
Compact neural networks are inclined to exploit “sparsely-connected” convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard “fully-connected” convolutions, these convolutions are more computationally economical. However, “sparsely-connected” convolutions block the inter-group information exchange, which induces severe performance degradation. To address this issue, we present two novel operations named merging and evolution to leverage the inter-group information. Our key idea is encoding the inter-group information with a narrow feature map, then combining the generated features with the original network for better representation. Taking advantage of the proposed operations, we then introduce the Merging-and-Evolution (ME) module, an architectural unit specifically designed for compact networks. Finally, we propose a family of compact neural networks called MENet based on the ME modules. Extensive experiments on CIFAR, SVHN, ILSVRC 2012, and PASCAL VOC 2007 datasets demonstrate that MENet consistently outperforms other state-of-the-art compact networks under different computational budgets. For instance, under the computational budget of 140 MFLOPs, MENet surpasses ShuffleNet by 1% and MobileNet by 1.95% on ILSVRC 2012 top-1 accuracy, while by 2.9% and 4.1% on PASCAL VOC 2007 mAP, respectively.