Loading [MathJax]/extensions/MathZoom.js
Yunsheng Li - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Yunsheng Li

Publications
9
Citations
709
Publications by Year
20172025
Co-Authors:
Show All Co-Authors (22)
Image of author Yunsheng Li

Yunsheng Li

Affiliation

Microsoft GenAI
Redmond
WA, USA

Publication Topics

Biography

Yunsheng Li received the Ph.D. degree from the University of California at San Diego in 2021. He is currently doing his research with Microsoft Cloud AI, Redmond. His research interests include vision language model, segmentation, and domain adaptation.(Based on document published on 9 April 2025).
Publications
9
Citations
709
Publications by Year
20172025
Co-Authors:
Show All Co-Authors (22)
Author's Published Works

Showing 1-9 of 9 results

  • Sort

Filter Results

Show

Sort By

Results

Pluralistic Salient Object Detection

Xuelu Feng;Yunsheng Li;Dongdong Chen;Chunming Qiao;Junsong Yuan;Lu Yuan;Gang Hua

IEEE Transactions on Image Processing
Year: 2025 | Volume: 34 | Journal Article |
We introduce pluralistic salient object detection (PSOD), a novel task aimed at generating multiple plausible salient segmentation results for a given input image. Unlike conventional SOD methods that produce a single segmentation mask for salient objects, this new setting recognizes the inherent complexity of real-world images, comprising multiple objects, and the ambiguity in defining salient ob...Show More

Pluralistic Salient Object Detection

Xuelu Feng;Yunsheng Li;Dongdong Chen;Chunming Qiao;Junsong Yuan;Lu Yuan;Gang Hua

Year: 2025 | Volume: 34 | Journal Article |

Dense Network Expansion for Class Incremental Learning

Zhiyuan Hu;Yunsheng Li;Jiancheng Lyu;Dashan Gao;Nuno Vasconcelos

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2023 | Conference Paper |
Cited by: Papers (25)
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is added per task. While effective from a computational standpoint, these methods lead to models that grow quickly with the number of tasks. A new NE method, dense network expansion (DNE), is proposed to achieve a better trade...Show More

Dense Network Expansion for Class Incremental Learning

Zhiyuan Hu;Yunsheng Li;Jiancheng Lyu;Dashan Gao;Nuno Vasconcelos

Year: 2023 | Conference Paper |

MicroNet: Improving Image Recognition with Extremely Low FLOPs

Yunsheng Li;Yinpeng Chen;Xiyang Dai;Dongdong Chen;Mengchen Liu;Lu Yuan;Zicheng Liu;Lei Zhang;Nuno Vasconcelos

2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Year: 2021 | Conference Paper |
Cited by: Papers (59)
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function, are effective to improve the accuracy. The former avoids the significant reduction of network width, while the latter mitigates the detriment of reduction in n...Show More

MicroNet: Improving Image Recognition with Extremely Low FLOPs

Yunsheng Li;Yinpeng Chen;Xiyang Dai;Dongdong Chen;Mengchen Liu;Lu Yuan;Zicheng Liu;Lei Zhang;Nuno Vasconcelos

Year: 2021 | Conference Paper |

Dynamic Transfer for Multi-Source Domain Adaptation

Yunsheng Li;Lu Yuan;Yinpeng Chen;Pei Wang;Nuno Vasconcelos

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2021 | Conference Paper |
Cited by: Papers (51)
Recent works of multi-source domain adaptation focus on learning a domain-agnostic model, of which the parameters are static. However, such a static model is difficult to handle conflicts across multiple domains, and suffers from a performance degradation in both source domains and target domain. In this paper, we present dynamic transfer to address domain conflicts, where the model parameters are...Show More

Dynamic Transfer for Multi-Source Domain Adaptation

Yunsheng Li;Lu Yuan;Yinpeng Chen;Pei Wang;Nuno Vasconcelos

Year: 2021 | Conference Paper |

Explainable Object-Induced Action Decision for Autonomous Vehicles

Yiran Xu;Xiaoyin Yang;Lihang Gong;Hsuan-Chu Lin;Tz-Ying Wu;Yunsheng Li;Nuno Vasconcelos

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2020 | Conference Paper |
Cited by: Papers (68)
A new paradigm is proposed for autonomous driving. The new paradigm lies between the end-to-end and pipelined approaches, and is inspired by how humans solve the problem. While it relies on scene understanding, the latter only considers objects that could originate hazard. These are denoted as action inducing, since changes in their state should trigger vehicle actions. They also define a set of e...Show More

Explainable Object-Induced Action Decision for Autonomous Vehicles

Yiran Xu;Xiaoyin Yang;Lihang Gong;Hsuan-Chu Lin;Tz-Ying Wu;Yunsheng Li;Nuno Vasconcelos

Year: 2020 | Conference Paper |

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
Year: 2020 | Volume: 42, Issue: 12 | Journal Article |
Cited by: Papers (12)
The transfer of a neural network (CNN) trained to recognize objects to the task of scene classification is considered. A Bag-of-Semantics (BoS) representation is first induced, by feeding scene image patches to the object CNN, and representing the scene image by the ensuing bag of posterior class probability vectors (semantic posteriors). The encoding of the BoS with a Fisher vector (FV) is then s...Show More

Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes

Mandar Dixit;Yunsheng Li;Nuno Vasconcelos

Year: 2020 | Volume: 42, Issue: 12 | Journal Article |

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Yunsheng Li;Lu Yuan;Nuno Vasconcelos

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2019 | Conference Paper |
Cited by: Papers (430)
Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or yield not so good performance compared with supervised learning. In this paper, we propose a novel bidirectional learning framework for domain adaptation of segme...Show More

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

Yunsheng Li;Lu Yuan;Nuno Vasconcelos

Year: 2019 | Conference Paper |

Efficient Multi-Domain Learning by Covariance Normalization

Yunsheng Li;Nuno Vasconcelos

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2019 | Conference Paper |
Cited by: Papers (22)
The problem of multi-domain learning of deep networks is considered. An adaptive layer is induced per target domain and a novel procedure, denoted covariance normalization (CovNorm), proposed to reduce its parameters. CovNorm is a data driven method of fairly simple implementation, requiring two principal component analyzes (PCA) and fine-tuning of a mini-adaptation layer. Nevertheless, it is show...Show More

Efficient Multi-Domain Learning by Covariance Normalization

Yunsheng Li;Nuno Vasconcelos

Year: 2019 | Conference Paper |

Deep Scene Image Classification with the MFAFVNet

Yunsheng Li;Mandar Dixit;Nuno Vasconcelos

2017 IEEE International Conference on Computer Vision (ICCV)
Year: 2017 | Conference Paper |
Cited by: Papers (42)
The problem of transferring a deep convolutional network trained for object recognition to the task of scene image classification is considered. An embedded implementation of the recently proposed mixture of factor analyzers Fisher vector (MFA-FV) is proposed. This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner. The new architecture involves...Show More

Deep Scene Image Classification with the MFAFVNet

Yunsheng Li;Mandar Dixit;Nuno Vasconcelos

Year: 2017 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.