Dayan Guan (官大衍)

alt text 

Research Fellow,
NTU-PKU Joint Research Institute,
Nanyang Technological University, Singapore

E-mail: dayan.guan@outlook.com

Google Scholar

GitHub

News

About Me

I am currently working as a Research Fellow at Nanyang Technological University, collaborating with Prof. Alex Kot. Prior to this position, I served as a Research Scientist at MBZUAI from Mar 2022 to July 2023 and a Research Fellow at Nanyang Technological University from Nov 2019 to Mar 2022, working with Prof. Shijian Lu. I received my PhD at Zhejiang University in Sep 2019, supervised by Prof. Yanpeng Cao, Prof. Jiangxin Yang, and Prof. Yanlong Cao. I obtained my bachelor's degree from Central South University in Jun 2014.

Research Statement

My research interests encompass scene understanding, unsupervised learning and multimodality. My goal is to develop techniques that can interpret complex scenes across various modalities with minimal human supervision.

Towards this goal, (I) during my doctoral studies, I focused on designing object detectors capable of processing visible and infrared images, particularly in situations where human-annotated labels were limited or unavailable. (II) Since graduating, I have been dedicated to developing unsupervised algorithms for object detection and semantic segmentation that can facilitate learning from unlabeled data across multiple modalities, such as images, videos and point clouds. (III) Most recently, I have been exploring the potential of unlabeled data to enhance the efficiency of large-scale vision-language models in various application fields.

Research Interests

  • Scene Understanding: Semantic Segmentation, Object Detection

  • Unsupervised Learning: Unsupervised Domain Adaptation, Semi-Supervised Learning

  • Multimodality: Images, Videos, Point Clouds, Vision-Language Pairs, RGB-IR Pairs

Refereed Publications

  1. Aoran Xiao*, Jiaxing Huang*, Dayan Guan, Xiaoqin Zhang, Shijian Lu†, Ling Shao. "Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey." IEEE TPAMI, 2023. [pdf] [code]

  2. Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu†, Eric Xing. "3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds." CVPR, 2023. [pdf] [code]

  3. Rumeng Yi, Dayan Guan, Yaping Huang†, Shijian Lu. "Class-independent Regularization for Learning with Noisy Labels." AAAI, 2023. [pdf] [code]

  4. Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu†, Ling Shao. "PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds." NeurIPS, 2022. [pdf] [code]

  5. Jiaxing Huang, Kaiwen Cui, Dayan Guan, Aoran Xiao, Fangneng Zhan, Shijian Lu†, Shengcai Liao, Eric Xing. "Masked Generative Adversarial Networks are Data-Efficient Generation Learners." NeurIPS, 2022. [pdf]

  6. Yun Xing*, Dayan Guan*, Jiaxing Huang, Shijian Lu†. "Domain Adaptive Video Segmentation via Temporal Pseudo Supervision." ECCV, 2022.[pdf][code]

  7. Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu†. "Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation." CVPR, 2022.[pdf][code]

  8. Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu†, Ling Shao. "Category Contrast for Unsupervised Domain Adaptation in Visual Tasks." CVPR, 2022. [pdf] [code]

  9. Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu†. "Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data." NeurIPS, 2021. [pdf] [code]

  10. Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu†. "Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation." AAAI, 2022. [pdf] [code]

  11. Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu†. "Domain Adaptive Video Segmentation via Temporal Consistency Regularization." ICCV, 2021. [pdf][code]

  12. Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu†. "RDA: Robust Domain Adaptation via Fourier Adversarial Attacking." ICCV, 2021. [pdf] [code]

  13. Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu†. Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection. IEEE Transactions on Multimedia, 2021. [pdf] [code]

  14. Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu†. "Cross-View Regularization for Domain Adaptive Panoptic Segmentation." CVPR, 2021. [pdf][code]

  15. Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu†. "FSDR: Frequency Space Domain Randomization for Domain Generalization." CVPR, 2021. [pdf][code]

  16. Dayan Guan, Jiaxing Huang, Shijian Lu†, Aoran Xiao. "Scale Variance Minimization for Unsupervised Domain Adaptation in Image Segmentation." Pattern Recognition, 2021. [pdf] [code]

  17. Dayan Guan, Yanpeng Cao†, Jiangxin Yang, Yanlong Cao, and Michael Ying Yang. "Fusion of Multispectral Data through Illumination-aware Deep Neural Networks for Pedestrian Detection." Information Fusion, 2019. [pdf]

  18. Dayan Guan, Xing Luo, Yanpeng Cao, Jiangxin Yang, Yanlong Cao, George Vosselman, and Michael Ying Yang, “Unsupervised Domain Adaptation for Multispectral Pedestrian Detection.” CVPRW, 2019. [pdf]

  19. Yanpeng Cao, Dayan Guan, Weilin Huang, Jiangxin Yang, Yanlong Cao, and Yu Qiao†. "Pedestrian Detection with Unsupervised Multispectral Feature Learning using Deep Neural Networks." Information Fusion, 2019. [pdf]

  20. Yanpeng Cao, Dayan Guan, Yulun Wu, Jiangxin Yang†, Yanlong Cao, Michael Ying Yang. "Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection." ISPRS Journal of Photogrammetry and Remote Sensing, 2019. [pdf]

  21. Dayan Guan, Yanpeng Cao†, Jiangxin Yang, Yanlong Cao, and Christel-Loic Tisse. "Exploiting Fusion Architectures for Multispectral Pedestrian Detection and Segmentation." Applied Optics, 2018. (Editors' Pick) [pdf]

Note: * Equal contribution, † Corresponding author.

Full list of publications in Google Scholar.

Professional Service

Conference Reviewer

  • CVPR, ICCV, ECCV, NeurIPS

Journal Reviewer

  • IEEE TIP, IEEE TMM, IEEE TNNLS, IEEE TCSVT, Pattern Recognition