Songyang Zhang

Postdoctoral Fellow at Shanghai AI Laboratory, Shanghai, China.


He has joined OpenMMLab, Shanghai AI Laboratory, supervised by Prof. Dahua Lin and Dr. Kai Chen. He leads a team working on foundation model, includes the research and open-source platform. His team develops and maintains the OpenMMLab projects MMClassification and MMSelfSup.

He obtained his Ph.D. in Computer Science at the University of Chinese Academy of Science, in the joint program at PLUS Lab, ShanghaiTech University, supervised Prof. Xuming He in 2022. He got his B.Sc. degree in 2017, and worked at MC^2 Lab, Beihang University, under the supervision of Prof. Mai Xu. He also worked as the research intern in TuSimple, Tencent Youtu Lab, and Megvii Research.

Open positions at OpenMMLab include full-time researchers/engineers and interns, feel free to contact him through the email. Research directions include: model architecture design, self/semi/weak-supervised learning, vision-language pre-training, 2d/3d detection, segmentation, etc.


Nov 5, 2022 Recieved the Champion of large-scale fine-grained classification [Code1][Code2][Certificate].
Jul 8, 2022 Two papers are accepted by ECCV 2022.
Jul 1, 2022 One paper is accepted by ICIP 2022.
Jun 19, 2022 He has joined Shanghai AI Laboratory as the postdoctoral fellow.
Mar 1, 2022 One paper is accepted by CVPR 2022.
Sep 1, 2021 He has been selected to ICCV 2021 Doctoral Consortium.
Aug 1, 2021 One paper on Vision Transformer is accepted to NeurIPS 2021
May 1, 2021 One paper on Incremental Semantic Segmenntation is accepted to ACM MM 2021
Apr 1, 2021 One paper on Few-shot Video Classification is accepted to IJCAI 2021.
Mar 1, 2021 Two papers are accepted to CVPR 2021.

Selected Publications(Full List)

  1. ECCV
    Action Quality Assessment with Temporal Parsing Transformer
    Yang Bai, Desen Zhou, Songyang Zhang, Jian Wang, Errui Ding, and 2 more authors
    In Proceeding of the European Conference on Computer Vision (ECCV), 2022
  2. CVPR
    SGTR: End-to-end Scene Graph Generation with Transformer
    Rongjie Li, Songyang Zhang, and Xuming He
    In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  3. NeurIPS
    Dynamic Grained Encoder for Vision Transformers
    Lin Song*, Songyang Zhang*, Songtao Liu, Zeming Li, Xuming He, and 3 more authors
    In Proceeding of Advances in Neural Information Processing Systems (NeurIPS), 2021
  4. CVPR
    Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
    Songyang Zhang, Zeming Li, Shipeng Yan, Xuming He, and Jian Sun
    In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
  5. ICML
    LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
    Songyang Zhang, Shipeng Yan, and Xuming He
    In Proceeding of the 36th International Conference on Machine Learning (ICML),, 2019
  6. AAAI
    A Dual Attention Network With Semantic Embedding for Few-shot Learning
    Shipeng Yan*, Songyang Zhang*, and Xuming He
    In Proceeding of Association for the Advancement of Artificial Intelligence (AAAI), 2019