publications

2024

1. Rag-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model

   Jianhao Yuan, Shuyang Sun, Daniel Omeiza, Bo Zhao, Paul Newman, Lars Kunze, and Matthew Gadd

   RSS, 2024
2. SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model

   Bin Cao, Jianhao Yuan, Yexin Liu, Jian Li, Shuyang Sun, Jing Liu, and Bo Zhao

   arXiv preprint arXiv:2402.18068, 2024
3. kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies

   Zhongrui Gui, Shuyang Sun, Runjia Li, Jianhao Yuan, Zhaochong An, Karsten Roth, Ameya Prabhu, and Philip Torr

   arXiv preprint arXiv:2404.09447, 2024

4. 

   CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

   Shuyang Sun*, Runjia Li*, Philip Torr, Xiuye Gu, and Siyang Li

   In CVPR, 2024

   Bib PDF Code Website

   @inproceedings{clip_as_rnn,
     title = {CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor},
     author = {Sun*, Shuyang and Li*, Runjia and Torr, Philip and Gu, Xiuye and Li, Siyang},
     year = {2024},
     booktitle = {CVPR},
     selected = true,
     pdf = https://arxiv.org/pdf/2312.07661.pdf,
     website = https://torrvision.com/clip_as_rnn/,
     code = https://github.com/kevin-ssy/clip_as_rnn,
     preview = clip_as_rnn.jpg,
     highlight = true
   }

5. 

   Real-Fake: Effective Training Data Synthesis Through Distribution Matching

   Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, and Bo Zhao

   ICLR, 2024

   Bib PDF Code Website

   @article{yuan2023real,
     title = {Real-Fake: Effective Training Data Synthesis Through Distribution Matching},
     author = {Yuan, Jianhao and Zhang, Jie and Sun, Shuyang and Torr, Philip and Zhao, Bo},
     journal = {ICLR},
     year = {2024},
     selected = true,
     preview = realfake.jpg,
     website = https://torrvision.com/realfake/,
     pdf = https://arxiv.org/abs/2310.10402,
     code = https://github.com/baai-dcai/training-data-synthesis
   }

6. Lumix: Improving mixup by better modelling label uncertainty

   Shuyang Sun*, Jie-Neng Chen*, Ruifei He, Alan Yuille, Philip Torr, and Song Bai

   ICASSP, 2024

   Bib

   @article{sun2022lumix,
     title = {Lumix: Improving mixup by better modelling label uncertainty},
     author = {Sun*, Shuyang and Chen*, Jie-Neng and He, Ruifei and Yuille, Alan and Torr, Philip and Bai, Song},
     journal = {ICASSP},
     year = {2024},
     thumbnails = true
   }

2023

1. 

   ReMaX: Relaxing for better training on efficient panoptic segmentation

   Shuyang Sun, Weijun Wang, Qihang Yu, Andrew Howard, Philip Torr, and Liang-Chieh Chen

   NeurIPS, 2023

   Bib PDF Website

   @article{sun2023remax,
     title = {ReMaX: Relaxing for better training on efficient panoptic segmentation},
     author = {Sun, Shuyang and Wang, Weijun and Yu, Qihang and Howard, Andrew and Torr, Philip and Chen, Liang-Chieh},
     journal = {NeurIPS},
     year = {2023},
     selected = true,
     pdf = https://arxiv.org/pdf/2306.17319.pdf,
     website = https://nips.cc/virtual/2023/poster/71598,
     preview = remax.jpg
   }

2. OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?

   Runjia Li*, Shuyang Sun*, Mohamed Elhoseiny, and Philip Torr

   In ICCV, 2023

   Bib

   @inproceedings{li2023oxfordtvg,
     title = {OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?},
     author = {Li*, Runjia and Sun*, Shuyang and Elhoseiny, Mohamed and Torr, Philip},
     booktitle = {ICCV},
     pages = {20293--20303},
     year = {2023},
   }

3. 

   Is synthetic data from generative models ready for image recognition?

   Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, and Xiaojuan Qi

   ICLR, spotlight, 2023

   Bib PDF Code

   @article{he2022synthetic,
     title = {Is synthetic data from generative models ready for image recognition?},
     author = {He, Ruifei and Sun, Shuyang and Yu, Xin and Xue, Chuhui and Zhang, Wenqing and Torr, Philip and Bai, Song and Qi, Xiaojuan},
     journal = {ICLR, spotlight},
     year = {2023},
     selected = true,
     code = https://github.com/cvmi-lab/syntheticdata,
     pdf = https://arxiv.org/abs/2210.07574,
     preview = synthesis.png
   }

2022

1. Slot-vps: Object-centric representation learning for video panoptic segmentation

   Yi Zhou, Hui Zhang, Hana Lee, Shuyang Sun, Pingjun Li, Yangguang Zhu, ByungIn Yoo, Xiaojuan Qi, and Jae-Joon Han

   In CVPR, 2022

   Bib

   @inproceedings{zhou2022slot,
     title = {Slot-vps: Object-centric representation learning for video panoptic segmentation},
     author = {Zhou, Yi and Zhang, Hui and Lee, Hana and Sun, Shuyang and Li, Pingjun and Zhu, Yangguang and Yoo, ByungIn and Qi, Xiaojuan and Han, Jae-Joon},
     booktitle = {CVPR},
     pages = {3093--3103},
     year = {2022},
   }

2. Knowledge distillation as efficient pre-training: Faster convergence, higher data-efficiency, and better transferability

   Ruifei He, Shuyang Sun, Jihan Yang, Song Bai, and Xiaojuan Qi

   In CVPR, 2022

   Bib

   @inproceedings{he2022knowledge,
     title = {Knowledge distillation as efficient pre-training: Faster convergence, higher data-efficiency, and better transferability},
     author = {He, Ruifei and Sun, Shuyang and Yang, Jihan and Bai, Song and Qi, Xiaojuan},
     booktitle = {CVPR},
     pages = {9161--9171},
     year = {2022},
   }

3. Patch-based separable transformer for visual recognition

   Shuyang Sun, Xiaoyu Yue, Hengshuang Zhao, Philip Torr, and Song Bai

   T-PAMI, 2022

   Bib

   @article{sun2022patch,
     title = {Patch-based separable transformer for visual recognition},
     author = {Sun, Shuyang and Yue, Xiaoyu and Zhao, Hengshuang and Torr, Philip and Bai, Song},
     journal = {T-PAMI},
     year = {2022},
     publisher = {IEEE},
   }

2021

1. 

   TransMix: Attend to Mix for Vision Transformers

   Shuyang Sun*, Jie-Neng Chen*, Ju He, Philip Torr, Alan Yuille, and Song Bai

   CVPR, 2021

   Bib PDF Code

   @article{chen2021transmix,
     title = {TransMix: Attend to Mix for Vision Transformers},
     author = {Sun*, Shuyang and Chen*, Jie-Neng and He, Ju and Torr, Philip and Yuille, Alan and Bai, Song},
     journal = {CVPR},
     year = {2021},
     selected = true,
     pdf = https://arxiv.org/pdf/2111.09833.pdf,
     code = https://github.com/beckschen/transmix,
     preview = transmix.jpg
   }

2. 

   Visual Parser: Representing Part-whole Hierarchies with Transformers

   Shuyang Sun, Xiaoyu Yue, Song Bai, and Philip Torr

   arXiv preprint arXiv:2107.05790, 2021

   Bib PDF Code

   @article{sun2021visual,
     title = {Visual Parser: Representing Part-whole Hierarchies with Transformers},
     author = {Sun, Shuyang and Yue, Xiaoyu and Bai, Song and Torr, Philip},
     journal = {arXiv preprint arXiv:2107.05790},
     year = {2021},
     selected = true,
     preview = vip.png,
     pdf = https://arxiv.org/abs/2107.05790,
     code = https://github.com/kevin-ssy/vip
   }

3. 

   Vision transformer with progressive sampling

   Xiaoyu Yue*, Shuyang Sun*, Zhanghui Kuang, Meng Wei, Philip Torr, Wayne Zhang, and Dahua Lin

   In ICCV, 2021

   Bib PDF Code

   @inproceedings{yue2021vision,
     title = {Vision transformer with progressive sampling},
     author = {Yue*, Xiaoyu and Sun*, Shuyang and Kuang, Zhanghui and Wei, Meng and Torr, Philip and Zhang, Wayne and Lin, Dahua},
     booktitle = {ICCV},
     pages = {387--396},
     year = {2021},
     selected = true,
     preview = psvit.png,
     pdf = https://arxiv.org/abs/2108.01684,
     code = https://github.com/yuexy/ps-vit
   }

4. Aggregation with Feature Detection

   Shuyang Sun, Xiaoyu Yue, Xiaojuan Qi, Wanli Ouyang, Victor Adrian Prisacariu, and Philip Torr

   In ICCV, 2021

   Bib

   @inproceedings{sun2021aggregation,
     title = {Aggregation with Feature Detection},
     author = {Sun, Shuyang and Yue, Xiaoyu and Qi, Xiaojuan and Ouyang, Wanli and Prisacariu, Victor Adrian and Torr, Philip},
     booktitle = {ICCV},
     pages = {527--536},
     year = {2021},
   }

2020

1. Exploring the hierarchy in relation labels for scene graph generation

   Yi Zhou, Shuyang Sun, Chao Zhang, Yikang Li, and Wanli Ouyang

   arXiv preprint arXiv:2009.05834, 2020

   Bib

   @article{zhou2020exploring,
     title = {Exploring the hierarchy in relation labels for scene graph generation},
     author = {Zhou, Yi and Sun, Shuyang and Zhang, Chao and Li, Yikang and Ouyang, Wanli},
     journal = {arXiv preprint arXiv:2009.05834},
     year = {2020},
   }

2. Learning to sample the most useful training patches from images

   Shuyang Sun, Liang Chen, Gregory Slabaugh, and Philip Torr

   arXiv preprint arXiv:2011.12097, 2020

   Bib

   @article{sun2020learning,
     title = {Learning to sample the most useful training patches from images},
     author = {Sun, Shuyang and Chen, Liang and Slabaugh, Gregory and Torr, Philip},
     journal = {arXiv preprint arXiv:2011.12097},
     year = {2020},
   }

2019

1. Hybrid task cascade for instance segmentation

   Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, and  others

   In CVPR, 2019

   Bib

   @inproceedings{chen2019hybrid,
     title = {Hybrid task cascade for instance segmentation},
     author = {Chen, Kai and Pang, Jiangmiao and Wang, Jiaqi and Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and Liu, Ziwei and Shi, Jianping and Ouyang, Wanli and others},
     booktitle = {CVPR},
     pages = {4974--4983},
     year = {2019},
   }

2. MMDetection: Open mmlab detection toolbox and benchmark

   Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, and  others

   arXiv preprint arXiv:1906.07155, 2019

   Bib

   @article{chen2019mmdetection,
     title = {MMDetection: Open mmlab detection toolbox and benchmark},
     author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and Liu, Ziwei and Xu, Jiarui and others},
     journal = {arXiv preprint arXiv:1906.07155},
     year = {2019},
   }

3. Robust multi-modality multi-object tracking

   Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, and Chen Change Loy

   In ICCV, 2019

   Bib

   @inproceedings{zhang2019robust,
     title = {Robust multi-modality multi-object tracking},
     author = {Zhang, Wenwei and Zhou, Hui and Sun, Shuyang and Wang, Zhe and Shi, Jianping and Loy, Chen Change},
     booktitle = {ICCV},
     pages = {2365--2374},
     year = {2019},
   }

2018

1. 

   Fishnet: A versatile backbone for image, region, and pixel level prediction

   Shuyang Sun, Jiangmiao Pang, Jianping Shi, Shuai Yi, and Wanli Ouyang

   NeurIPS, 2018

   Bib PDF Code

   @article{sun2018fishnet,
     title = {Fishnet: A versatile backbone for image, region, and pixel level prediction},
     author = {Sun, Shuyang and Pang, Jiangmiao and Shi, Jianping and Yi, Shuai and Ouyang, Wanli},
     journal = {NeurIPS},
     volume = {31},
     year = {2018},
     selected = true,
     pdf = https://arxiv.org/pdf/1901.03495.pdf,
     code = https://github.com/kevin-ssy/fishnet,
     preview = fish.png
   }

2. 

   Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition

   Shuyang Sun, Zhanghui Kuang, Lu Sheng, Wanli Ouyang, and Wei Zhang

   In CVPR, 2018

   Bib PDF Code

   @inproceedings{sun2018optical,
     title = {Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition},
     author = {Sun, Shuyang and Kuang, Zhanghui and Sheng, Lu and Ouyang, Wanli and Zhang, Wei},
     booktitle = {CVPR},
     year = {2018},
     selected = true,
     pdf = https://arxiv.org/pdf/1711.11152.pdf,
     code = https://github.com/kevin-ssy/optical-flow-guided-feature,
     preview = off.jpg
   }

2017

1. Spindle net: Person re-identification with human body region guided feature decomposition and fusion

   Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, and Xiaoou Tang

   In CVPR, 2017

   Bib

   @inproceedings{zhao2017spindle,
     title = {Spindle net: Person re-identification with human body region guided feature decomposition and fusion},
     author = {Zhao, Haiyu and Tian, Maoqing and Sun, Shuyang and Shao, Jing and Yan, Junjie and Yi, Shuai and Wang, Xiaogang and Tang, Xiaoou},
     booktitle = {CVPR},
     pages = {1077--1085},
     year = {2017},
   }