Home People Research Publications Demos
         
News Jobs Prospective
Students
About Internal

Yunsheng Li

Department of Electrical and Computer Engineering,
University of California, San Diego
9500 Gilman Drive, Mail code 0409
La Jolla, CA 92093-0409

EBU 1, Room 4604

Email: yul554@eng.ucsd.edu
Phone: (858) 247-9813


Bio:

I am currently a Ph.D student at Statistical Visual Computing Lab, Department of Electrical and Computer Engineering at University of California, San Diego (UCSD), under the supervision of Prof. Nuno Vasconcelos. Before I start my Ph.D program, I get my Master Degree in SVCL in 2017.

Research:

My research interest is about computer vision especially about transfor learning and efficient network design. The target of transfer learning is to use a well pretrained model for other tasks with (continuous learning) or without supervision (domain adaptation). For efficient network design, the research target is to design a computational and memory efficient network backbond for classification, object detection and segmenataion tasks. Currently, I focus on the research problem about the design of efficient object detector especially the computation happened in the detector head.

Publications:

Dynamic Transfer for Multi-Source Domain Adaptation
Yunsheng Li, Lu Yuan, Yinpeng Chen, Pei Wang, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Virtual, 2021, (online)
[ paper | BibTex | Code]

Revisiting Dynamic Convolution via Matrix Decomposition
Yunsheng Li, Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Ye Yu, Zicheng Liu, Mei Chen, Lu Yuan, Nuno Vasconcelos
International Conference on Learning Representations (ICLR)
Virtual, 2021, (online)
[ paper | BibTex | Code]

Explainable Object-induced Action Decision for Autonomous Vehicles
Yiran Xu, Xiaoyin Yang, Lihang Gong, Hsuan-Chu Lin, Tz-Ying Wu, Yungsheng Li, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Seattle, United States, 2020 (online)
[ Website | paper | BibTeX | code ]

Bidirectional Learning for Domain Adaptation of Semantic Segmentation
Yunsheng Li, Lu Yuan, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Long Beach, US, 2019
[ paper | BibTex | Code]

Efficient Multi-Domain Learning by Covariance Normalization
Yunsheng Li Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Long Beach, US, 2019
[ paper | BibTex | Code ]

Deep scene image classification with the mfafvnet
Yunsheng Li, Mandar Dixit, Nuno Vasconcelos
International Conference on Computer Vision (ICCV)
Venice, Italy, 2017
[ paper | BibTex ]

Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings
Pedro Morgado, Yunsheng Li, Jose Costa Pereira, Mohammad Saberian, Nuno Vasconcelos
International Journal of Computer Vision (IJCV)
[ paper | BibTex]

Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes
Mandar Dixit, Yunsheng Li, Nuno Vasconcelos
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
[ paper | BibTex]

Last update: July, 2018





© SVCL