About Me
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 interned at International Digital Economy Academy, Shenzhen (advised by Prof. Lei Zhang) and Microsoft Research, Redmond (advised by Dr. Jianwei Yang and Dr. Chunyuan Li). 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 computer vision, especially in fine-grained understanding to perceive the world, like object detection, segmentation, and multi-modal learning.
🔥 News
- [2023/4]: DINO ranks 2nd among the most influential ICLR 2023 papers.
- [2023/3]: DINO and DN-DETR are selected as the top 100 most cited AI papers for 2022, rank 38 and 53, respectively.
- [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 (COCO instance, COCO panoptic, and ADE20K semantic)! 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. Code is available here.
- [2022/3]: Our DN-DETR is selected for an oral presentation in CVPR 2022! Code is now available here.
📝 Recent Works
Refer to my google scholar for the full list.
SEEM: Segment Everything Everywhere All at Once.
Xueyan Zou*, Jianwei Yang*, Hao Zhang*, Feng Li*, Linjie Li, Jianfeng Gao, Yong Jae Lee.
arxiv 2023.
[Paper][Code]Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang.
arxiv 2023.
[Paper][Code]Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR.
Feng Li, Ailing Zeng, Shilong Liu, Hao Zhang, Lei Zhang, Lionel M. Ni.
CVPR 2023.
[Paper][Code]MP-Former: Mask-Piloted Transformer for Image Segmentation.
Hao Zhang*, Feng Li*, Huaizhe Xu, Shijia Huang, Shilong Liu, Lionel M. Ni, Lei Zhang.
CVPR 2023.
[Paper][Code]
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.
CVPR 2023.
[Paper][Code]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.
ICLR 2023.
[Paper][Code] Rank 2nd on ICLR 2023 Most Inflentical PapersVision-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.
arxiv 2022.
[Paper]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.
[Paper][Code]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.
[Paper][Code]
(* denotes equal contribution.)
🎖 Selected Awards
- Hong Kong Postgraduate Scholoarship, 2021
- Contemporary Undergraduate Mathematical Contest in Modeling(CUMCM), National first prize, 2019.