I’m a second-year PhD (2021-now) student at the Department of Computer Science & Engineering, Hong Kong University of Science and Technology, co-supervised by Prof. Heung-Yeung Shum and Prof. Lionel M. Ni. I am an intern at International Digital Economy Academy (IDEA), advised by Prof. Lei Zhang. Previously, I obtained my bachelor’s degree from Computer Science and Technology, South China University of Science and Technology in 2021.
My research interests lie in machine learning, computer vision, object detection, and multi-modal learning.
- [2023/3]: Three papers accepted to CVPR 2023! Check out our Mask DINO , Lite DETR, and MP-Former.
- [2023/1]: Two papers accepted to ICLR 2023! Check out our DINO and ED-Pose.
- [2022/6]: Checkout our unified detection and segmentation model Mask DINO that achieves SOTA results on all the three segmentation tasks (54.5 AP on COCO instance leaderboard, 59.4 PQ on COCO panoptic leaderboard, and 60.8 mIoU on ADE20K semantic leaderboard)! Code is available here.
- [2022/3]: We release DINO that for the first time establishes a DETR-like model as a SOTA model on the COCO object detection leaderboard with 63.3 AP. Code is available here.
- [2022/3]: Our DN-DETR is selected for an oral presentation in CVPR 2022! Code is now avaliable here.
- [2022/3]: We build a new repo awesome Detection Transformer to present papers about transformer for detection and segmenttion.
- [2022/3]: We release a survey Vision-Language Intelligence: Tasks, Representation Learning, and Large Models;
- [2022/1]: DAB-DETR is accepted by ICLR 2022;
📝 Selected Publications
Refer to my google scholar for full publication list.
Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR.
Feng Li, Ailing Zeng, Shilong Liu, Hao Zhang, Lei Zhang, Lionel M. Ni.
MP-Former: Mask-Piloted Transformer for Image Segmentation.
Hao Zhang*, Feng Li*, Huaizhe Xu, Shijia Huang, Shilong Liu, Lionel M. Ni, Lei Zhang.
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation.
Feng Li*, Hao Zhang*, Huaizhe Xu, Shilong Liu, Lei Zhang, Lionel M. Ni, Heung-Yeung Shum.
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection.
Hao Zhang*, Feng Li*, Shilong Liu*, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, Heung-Yeung Shum.
Vision-Language Intelligence: Tasks, Representation Learning, and Large Models.
Feng Li*, Hao Zhang*, Yi-Fan Zhang, Shilong Liu, Jian Guo, Lionel M Ni, PengChuan Zhang, Lei Zhang.
DN-DETR: Accelerate DETR Training by Introducing Query DeNoising.
Feng Li*, Hao Zhang*, Shilong Liu, Jian Guo, Lionel M. Ni, Lei Zhang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022. Oral presentation.
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR.
Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi, Hang Su, Jun Zhu, Lei Zhang.
International Conference on Learning Representations (ICLR) 2022.
(* denotes equal contribution.)
🎖 Selected Awards
- Hong Kong Postgraduate Scholoarship, 2021
- Contemporary Undergraduate Mathematical Contest in Modeling(CUMCM), National first prize, 2019.