Avatar

Yibo Yang

ibo AT pku.edu.cn

Algorithm Scientist

JD Explore Academy

Biography

Currently, I am a fourth-year graduate student at Center for Data Science, Academy for Advanced Interdisciplinary Studies, Peking University. I am co-supervised by Prof. Zhouchen Lin and Dongmin Chen, and do researches on computer vision and machine learning. I obtained my bachelor’s degree of applied physics from Nanjing University of Information Science & Technology in 2016.

Interests

  • Computer Vision
  • Machine Learning

Education

  • Ph.D. candidate in Data Science (Computer Science and Technology), 2016 - 2021

    Peking University

  • Bsc in Applied Physics, 2012 - 2016

    Nanjing University of Information Science & Technology

Publications @ZERO Lab

Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks. ICLR, 2023.

Endowing deep learning models with symmetry priors can lead to a considerable performance improvement. As an interesting bridge between …

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search. CVPR, 2021.

Most differentiable neural architecture search methods construct a super-net for search and derive a target-net as its sub-graph for …

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding. NeurIPS, 2020.

Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate …

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation. CVPR, 2020.

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such …

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families. AAAI, 2020.

Inspired from the dynamical systems, this study aims to unravel and improve ResNets.

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation. AAAI, 2020.

Our study aims to explicitly predict overlap relations and resolve overlaps in a differentiable way for the panoptic output.

Expectation Maximization Attention Networks for Semantic Segmentation. ICCV, 2019.

We formulate the attention mechanism into an expectation-maximization manner and iteratively estimate a much more compact set of bases …

Convolutional Neural Networks with Alternately Updated Clique. CVPR, 2018.

We propose a new convolutional neural network architecture with alternately updated clique (CliqueNet)

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution. NIPS, 2018.

We propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in …

Optimization Algorithm Inspired Deep Neural Network Structure Design. ACML, 2018.

In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a …

Talks

COCO2019. 2019.

Panoptic Segmentation Innovative Award

COCO2018. 2018.

Panoptic Segmentation Runner-Up

Awards

PKU_ZERO team won the Innovative Award of panoptic segmentation in COCO 2019 challenge, 2019

Members: Yibo Yang, Xia Li, Hongyang Li, Tiancheng Shen, Zhouchen Lin

PKU_360 team won the 3-rd place of panoptic segmentation in COCO 2018 challenge, 2018

Members: Yibo Yang, Xia Li, Hongyang Li, Tiancheng Shen, Zhouchen Lin, Jian Dong, Jiashi Feng, Shuicheng Yan

Most Popular Poster Award in VALSE 2018, Second Prize (top 3 in 145), 2018

American Interdiscipilinary Contest in Modeling, Finalist Award, 2015

Jiangsu Provincial Advanced Mathematics Contest, Second Prize, 2014