I am a Ph.D. student at University of California, Santa Cruz (UCSC), working with Professor Yang Liu. I am currently interested in weakly supervised learning (learning with imperfect information) and explainable neural networks (network understanding). Previously, I spent two years at YouTu Lab, Tencent, working with Ke Li and Xing Sun.


Two papers are available on arxiv: RMNet and SSL for Noisy Label.
One paper accepted to ICLR 2021.
One paper accepted to NeurlPS 2020.
One paper accepted to CVPR 2020.

Selected Publication (* denotes equal contribution)

Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR 2021)
Hao cheng*, Zhaowei Zhu*, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu.
paper code

Pruning Filter in Filter (NeurlPS 2020)
Fanxu Meng*, Hao Cheng*, Ke Li, Huixiang Luo, Xiaowei Guo, Guangming Lu, Xing Sun.
paper code

Filter Grafting for Deep Neural Networks (CVPR 2020)
Fanxu Meng*, Hao Cheng*, Ke Li, Zhixin Xu, Rongrong Ji, Xing Sun, Guangming Lu.
paper code

Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks (CVPR 2019)
Hao Cheng*, Dongze Lian*, Bowen Deng, Shenghua Gao, Tao Tan, Yanlin Geng.
paper code

Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane (ECCV 2018)
Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng.
paper code

Invited Talks

Invited talk by Stan Z. Li on Mutual Information in Deep Learning.

Invited talk by 机器之心 on Learning with Noisy Labels and Collaborative Learning.

Recent Awards

Chancellor Fellowship        UCSC       2021

Four-Star Distinguished Staff  Youtu Lab, Tencent    2020

Technology Breakthrough Award  Youtu Lab, Tencent   2020

Top-1 Lecturer of the Year    Youtu Lab, Tencent   2020