Dongshuo Yin (殷东硕)



Biography [Google Scholar]

Dongshuo Yin is currently a postdoc researcher in Tsinghua University, working with Prof. Shimin Hu at the Department of Computer Science and Technology. Before that, Dongshuo Yin received the PhD degree from School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences & Institute of Electronics (Aerospace Information Research Institute), Chinese Academy of Sciences, advised by Prof. Xian Sun. Dongshuo Yin's research interests include deep learning and computer vision, with a focus on remote sensing, parameter-efficient fine tuning, 3D weakly supervised object detection.

殷东硕,清华大学计算机系博士后,合作导师胡事民院士。2024年毕业于中国科学院空天信息创新研究院/中国科学院大学并获工学博士学位,导师为孙显研究员(国家杰青)。曾于2024年入选清华大学“水木学者”计划,并于同年获得“中国科学院院长奖”。曾于2023年至2024年在微软亚洲研究院(Microsoft Research Asia, MSRA)和阿里巴巴集团(Alibaba Group)进行科研合作交流。曾以一作身份在Nature子刊Nature Communications、IEEE CVPR、IEEE ICCV、ACM MM、IEEE TITS等国际顶级期刊/会议发表论文多篇,并担任NeurIPS、ICLR、IEEE TIP、IEEE TMM等多个国际出版物的审稿人。研究方向包括计算机视觉、遥感图像解译以及参数高效微调等领域。其中Nature子刊工作(全球垃圾堆检测与分析)曾被“中科院之声”、“腾讯新闻”、“网易新闻”、“搜狐新闻”报导,相关论文发表一年内已被阅读过万次。

如果对相关工作感兴趣,欢迎邮件联系我。同时,非常欢迎对科学研究感兴趣的清华本科生或外校研究生联系我进行线下(清华大学及五道口附近)或线上的合作交流。

🔥 News

📝 Publications

Revealing influencing factors on global waste distribution via deep-learning based dumpsite detection from satellite imagery
Xian Sun*, Dongshuo Yin*, Fei Qin, Hongfeng Yu, Wanxuan Lu, Fanglong Yao, Qibin He, Xingliang Huang, Zhiyuan Yan, Peijin Wang, Chubo Deng, Nayu Liu, Yiran Yang, Wei Liang, Ruiping Wang, Cheng Wang, Naoto Yokoya, Ronny Hänsch, Kun Fu
Nature Communications (Nat. Comm., IF=17.694, Co-first author with the supervisor)

TEA: A Training-Efficient Adapting Framework for Tuning Foundation Models in Remote Sensing
Leiyi Hu, Wanxuan Lu, Hongfeng Yu, Dongshuo Yin, Xian Sun, Kun Fu
IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS, CCF-B, IF=7.5)

5% > 100%: BreakingPerformance Shackles of Full Fine-Tuning on Visual Recognition Tasks
Dongshuo Yin, Leiyi Hu, Bin Li, Youqun Zhang, Xue Yang
ArXiv (Under Review)

Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions
Dongshuo Yin, Xueting Han, Bin Li, Hao Feng, Jing Bai
Proceedings of the ACM International Conference on Multimedia (ACM MM 2024, CCF-A, Main Track)

AiRs: Adapter in Remote Sensing for Parameter-Efficient Transfer Learning
Leiyi Hu, Hongfeng Yu, Wanxuan Lu, Dongshuo Yin, Xian Sun, Kun Fu
IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS, CCF-B, IF=7.5)

1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions
Dongshuo Yin, Yiran Yang, Zhechao Wang, Hongfeng Yu, Kaiwen Wei, Xian Sun
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE CVPR 2023, CCF-A, Main Track)

GAL: Graph-Induced Adaptive Learning for Weakly Supervised 3D Object Detection
Dongshuo Yin, Hongfeng Yu, Nayu Liu, Fanglong Yao, Qibin He, Jihao Li, Yiran Yang, Shiyao Yan, Xian Sun
IEEE Transactions on Intelligent Transportation Systems (IEEE TITS, CCF-B, IF=9.6)

Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation
Yiran Yang*, Dongshuo Yin*, Xuee Rong, Xian Sun, Wenhui Diao, Xinming Li
Proceedings of the IEEE/CVF International Conference on Computer Vision (IEEE ICCV 2023, CCF-A, Main Track)

Optimal Partition Assignment for Universal Object Detection
Yiran Yang, Xian Sun, Wenhui Diao, Xuee Rong, Shiyao Yan, Dongshuo Yin, Xinming Li
IEEE Transactions on MultiMedia (IEEE TMM, CCF-B, IF=8.4)

Statistical Sample Selection and Multivariate Knowledge Mining for Lightweight Detectors in Remote Sensing Imagery
Yiran Yang, Xian Sun, Wenhui Diao, Dongshuo Yin, Zhujun Yang, Xinming Li
IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS, CCF-B, IF=7.5)
🛠 Projects

Global Garbage Dump Detection
Organization: Aerospace Information Research Institute, Chinese Academy of Sciences
[Website]
💼 Work Experience

Microsoft Research Asia
Systems Research Group
Internship: 2023.3-2023.12

Alibaba Group
Intime BG
Internship: 2023.1-2023.3
🎓 Education

Sep. 2019 - June. 2024

Sep. 2024 - June. 2026
👓 Reviewer Services

  •   • IEEE Transactions on Multimedia (IEEE TMM).
  •   • Scientific Reports (Nature Portfolio Journals).
  •   • NeurIPS 2024.
  •   • ICLR 2025.
  •   • IEEE Transactions on Image Processing (IEEE TIP).
🎖 Awards

  •   • 2024: Shuimu Tsinghua Scholar for Postdoc Researcher (清华大学水木学者).
  •   • 2024: CAS President Scholarship (中国科学院院长奖).
  •   • 2020: Merit Student Award.
  •   • 2018: National Scholarship (0.3%).
  •   • 2018: American Mathematical Contest In Modeling (MCM) Honorable Mention Award.
  •   • 2017: First Prize of Anhui Competition Area in Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM).

Copyright © 2022   Dongshuo Yin. All Rights Reserved.