Shilong Liu

Self-intro of Shilong Liu

View the Project on GitHub SlongLiu/mycv


Shilong Liu (刘世隆)

Ph.D. student, Tsinghua University.

I’m a second-year Ph.D. student at the Department of Computer Science and Technology, Tsinghua University, under the supervision of Prof. Lei Zhang, Prof. Hang Su, and Prof. Jun Zhu. I got my bachelor’s degree from the Department of Industrial Engineering, Tsinghua University in 2020.

I am an intern of computer vision at International Digital Economy Academy (IDEA). I was an intern at Megvii Research in 2019.

My research interest includes machine learning, deep learning and their applications in computer vision.



Google Scholar:


[2022/3/13]: We release a strong open-set object detection model Grounding DINO that achieves the best results on open-set object detection tasks. It achieves 52.5 zero-shot AP on COCO detection, without any COCO training data! It achieves 63.0 AP on COCO after fine-tuning. Code and checkpoints will be available here.
[2022/9/22]: We release a toolbox detrex that provides state-of-the-art Transformer-based detection algorithms. It includes DINO with better performance. Welcome to use it!
[2023/2/28]: 4 papers are accepted to CVPR 2023!
[2023/1/21]: 2 papers are accepted to ICLR 2023!
[2022/11/19]: 1 paper is accepted to AAAI 2023!
[2022/6/7]: [CVPR 2023] We release a unified detection and segmentation model Mask DINO that achieves the best results on all the three segmentation tasks 54.7 AP on COCO instance leaderboard, 59.5 PQ on COCO panoptic leaderboard, and 60.8 mIoU on ADE20K semantic leaderboard! Code will be available here.
[2022/3/9]: We build a new repo awesome Detection Transformer to present papers about transformer for detection and segmenttion. Welcome to your attention!
[2022/3/8]: [ICLR 2023] Our DINO reach the SOTA on MS-COCO leader board with 63.3AP! Code is avaliable here!


Refer to my google scholar page for a full paper list.

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]

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation.
Jie Yang, Ailing Zeng, Shilong Liu, Feng Li, Ruimao Zhang, Lei Zhang
ICLR 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]

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
arxiv 2022.

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.
[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]

Query2Label: A Simple Transformer Way to Multi-Label Classification.
Shilong Liu, Lei Zhang, Xiao Yang, Hang Su and Jun Zhu.
arXiv, 2021.
[paper] [code]

Unsupervised Part Segmentation through Disentangling Appearance and Shape.
Shilong Liu, Lei Zhang, Xiao Yang, Hang Su and Jun Zhu.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Online (due to COVID-19), 2021.
[paper] [code]


Our team (Xiao Yang, Yichi Zhang, Chang Liu, Wenzhao Xiang, Shilong Liu) won the second place in the Unrestricted Adversarial Attacks on ImageNet Competition of CVPR-2021 AML-CV Workshop. (related paper)

Our team (Xiao Yang, Dingcheng Yang, Zihao Xiao, Yinpeng Dong, Shilong Liu) won the first place in the GeekPwn DeepFake competition (October 24th, 2020).


ICML 2023;
CVPR 2023, 2022, 2021;
ICCV 2023, 2021.
ECCV 2022.