Picture for Shusheng Yang

Shusheng Yang

ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers

May 24, 2023
Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang

Access Paper or Ask Questions

MobileInst: Video Instance Segmentation on the Mobile

Mar 30, 2023
Renhong Zhang, Tianheng Cheng, Shusheng Yang, Haoyi Jiang, Shuai Zhang, Jiancheng Lyu, Xin Li, Xiaowen Ying, Dashan Gao, Wenyu Liu, Xinggang Wang

Figure 1 for MobileInst: Video Instance Segmentation on the Mobile

Figure 2 for MobileInst: Video Instance Segmentation on the Mobile

Figure 3 for MobileInst: Video Instance Segmentation on the Mobile

Figure 4 for MobileInst: Video Instance Segmentation on the Mobile

* Preprint. 12 pages, 7 figures

Access Paper or Ask Questions

Temporally Efficient Vision Transformer for Video Instance Segmentation

Apr 18, 2022
Shusheng Yang, Xinggang Wang, Yu Li, Yuxin Fang, Jiemin Fang, Wenyu Liu, Xun Zhao, Ying Shan

Figure 1 for Temporally Efficient Vision Transformer for Video Instance Segmentation

Figure 2 for Temporally Efficient Vision Transformer for Video Instance Segmentation

Figure 3 for Temporally Efficient Vision Transformer for Video Instance Segmentation

Figure 4 for Temporally Efficient Vision Transformer for Video Instance Segmentation

* To appear in CVPR 2022

Access Paper or Ask Questions

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Apr 06, 2022
Yuxin Fang, Shusheng Yang, Shijie Wang, Yixiao Ge, Ying Shan, Xinggang Wang

Figure 1 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Figure 2 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Figure 3 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

Figure 4 for Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

* Preprint. Work in progress. Code and pre-trained models are available at \url{https://github.com/hustvl/MIMDet}

Access Paper or Ask Questions

Relational Surrogate Loss Learning

Feb 26, 2022
Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu

Figure 1 for Relational Surrogate Loss Learning

Figure 2 for Relational Surrogate Loss Learning

Figure 3 for Relational Surrogate Loss Learning

Figure 4 for Relational Surrogate Loss Learning

* Accepted to ICLR 2022

Access Paper or Ask Questions

Tracking Instances as Queries

Jun 23, 2021
Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Ying Shan, Bin Feng, Wenyu Liu

Figure 1 for Tracking Instances as Queries

Figure 2 for Tracking Instances as Queries

Figure 3 for Tracking Instances as Queries

Figure 4 for Tracking Instances as Queries

* CVPR 2021 Workshop. 2nd Place Solution for YouTube-VOS Challenge 2021: Video Instance Segmentation
* Preprint. Work in progress

Access Paper or Ask Questions

Instances as Queries

May 23, 2021
Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

Figure 1 for Instances as Queries

Figure 2 for Instances as Queries

Figure 3 for Instances as Queries

Figure 4 for Instances as Queries

* 14 pages, 8 figures, including the Appendix

Access Paper or Ask Questions

QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

May 16, 2021
Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

Figure 1 for QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

Figure 2 for QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

Figure 3 for QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

Figure 4 for QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

* Add results with Swin-L backbone, mask AP = 49.1 & box AP = 56.1 @ COCO test-dev

Access Paper or Ask Questions