Jiemin Fang (方傑民)

Email:
GitHub | Google Scholar | DBLP

I am a PhD candidate at the Institute of Artificial Intelligence and School of Electronic Information and Communications (EIC), Huazhong University of Science and Technology (HUST), supervised by Prof. Wenyu Liu and Prof. Xinggang Wang. I received my B.E. degree from EIC, HUST in 2018. My research interests mainly lie in efficient deep learning from neural architecture perspectives and neural rendering.

News

• Apr. 2022 - Our EfficientPose is chosen for the CVMJ 2021 best paper award.
• Mar. 2022 - Two papers are accepted by CVPR 2022.
• Jan. 2022 - BINGO is accepted by ICLR 2022.
• Jul. 2021 - One paper is accepted by ICCV 2021.
• Dec. 2020 - "FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search" is published in IEEE TPAMI.
• Nov. 2020 - I have released a PyTorch toolkit dali-pytorch for accelerating ImageNet training with NVIDIA DALI. It improves the training speed dramatically with maintaining high performance.

Publications

Journal Papers

• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
  Jiemin Fang*, Yuzhu Sun*, Qian Zhang, Kangjian Peng, Yuan Li, Wenyu Liu, Xinggang Wang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021 PDF | Code | BibTeX

• EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
  Jiemin Fang*, Yukang Chen*, Xinbang Zhang, Qian Zhang, Chang Huang, Gaofeng Meng, Wenyu Liu, Xinggang Wang
  SCIENCE CHINA Information Sciences (SCIS) 2021 PDF | Code | BibTeX

• EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
  Wenqiang Zhang*, Jiemin Fang*, Xinggang Wang, Wenyu Liu
  Computational Visual Media (CVMJ) 2021 (Best Paper Award) PDF | Code | BibTeX

Conference Papers

• MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
  Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang, Wenyu Liu, Qi Tian
  CVPR 2022 PDF | Code | BibTeX

• Bag of Instances Aggregation Boosts Self-supervised Learning
  Haohang Xu*, Jiemin Fang*, Xiaopeng Zhang, Lingxi Xie, Xinggang Wang, Wenrui Dai, Hongkai Xiong, Qi Tian
  ICLR 2022 PDF | Code | BibTeX

• Densely Connected Search Space for More Flexible Neural Architecture Search
  Jiemin Fang, Yuzhu Sun, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang
  CVPR 2020 PDF | Code | BibTeX

• Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
  Jiemin Fang*, Yuzhu Sun*, Kangjian Peng*, Qian Zhang, Yuan Li, Wenyu Liu, Xinggang Wang
  ICLR 2020 PDF | Code | BibTeX

• Temporally Efficient Vision Transformer for Video Instance Segmentation
  Shusheng Yang, Xinggang Wang, Yu Li, Yuxin Fang, Jiemin Fang, Wenyu Liu, Xun Zhao, Ying Shan
  CVPR 2022 (Oral) PDF | Code | BibTeX

• You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
  Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, Wenyu Liu
  NeurIPS 2021 PDF | Code | BibTeX

• Hierarchical Aggregation for 3D Instance Segmentation
  Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang
  ICCV 2021 PDF | Code | BibTeX

• Deep Multi-instance Learning with Dynamic Pooling
  Yongluan Yan, Xinggang Wang, Xiaojie Guo, Jiemin Fang, Wenyu Liu, Junzhou Huang
  ACML 2018 PDF | BibTeX

Preprints

• NeuSample: Neural Sample Field for Efficient View Synthesis
  Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang, Wenyu Liu, Qi Tian
  arXiv:2111.15552 PDF | Code | Project Page | BibTeX

• ResizeMix: Mixing Data with Preserved Object Information and True Labels
  Jie Qin*, Jiemin Fang*, Qian Zhang, Wenyu Liu, Xingang Wang, Xinggang Wang
  arXiv:2012.11101 PDF | BibTeX

Internships

• Jan. 2021 - present, Huawei Cloud in Shanghai working with Prof. Qi Tian, Dr. Lingxi Xie and Dr. Xiaopeng Zhang.
• Aug. 2018 - Nov. 2020, Horizon Robotics in Beijing working with Dr. Qian Zhang.

Academic Services

Reviewer of

• IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), Neural Networks, Image and Vision Computing, SCIENCE CHINA Information Sciences.
• NeurIPS 2022, ECCV 2022, ICML 2022, CVPR 2022, ICLR 2022, NeurIPS 2021, ICCV 2021, ICML 2021, CVPR 2021, AAAI 2021.

Competition Experience

• I ever participated in RoboMaster Robotics Competition. I worked on embedded development and achieved the national second prize in 2017. Then in 2018, I led the team to win the national second prize.

Awards

• National Scholarship for PhD Student, 2021
• National Scholarship for Master Student, 2020
• National Scholarship for Undergraduate Student, 2017

---

1. * denotes equal contribution. ↩

Since Feb. 2021