Yifan Zhang

Yifan Zhang is a final year Ph.D. candidate at CityUHK, working with Prof. HOU Junhui. He received his M.E. degree from Shanghai Jiao Tong University in 2019, advised by Prof. Chengliang Liu. He obtained his B.S. degree at Huazhong University of Science and Technology in 2016. He used to work in industry and had some grounding experience with algorithms. His research interests include computer vision, machine learning and robotics. He is open to collaborating with other researchers who are interested in related fields.

His current research interests primarily focus on

Computer Vision: 3D Scene Understanding, Multi-modal Fusion, Event-based Vision.

Machine Learning: Self-supervised Learning, Uncertainty in Artificial Intelligence, Adversarial Robustness

Intelligent Robotics: Autonomous Driving Perception, Robotic Manipulation and Navigation

Email / Github / Scholar / Twitter

Recent Projects
(*: Equal contribution †: Corresponding author)

	Self-supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration Yifan Zhang, Siyu Ren, Junhui Hou, Jinjian Wu, Yixuan Yuan, Guangming Shi Arxiv, 2024 paper / code

	Boosting 3D Object Detection with Semantic-Aware MultiBranch Framework Hao Jing, Anhong Wang, Lijun Zhao, Yakun Yang, Donghan Bu, Jing Zhang, Yifan Zhang, Junhui Hou Arxiv, 2024 paper

	Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models Yifan Zhang, Junhui Hou Advances in Neural Information Processing Systems (NeurIPS), 2024 paper / code

	Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Wu IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 paper / code

	Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 paper / code

	A Comprehensive Study of the Robustness for LiDAR-Based 3D Object Detectors Against Adversarial Attacks Yifan Zhang, Yixuan Yuan, Junhui Hou International Journal of Computer Vision (IJCV), 2024 paper / code

	Unleash the Potential of Image Branch for Cross-modal 3D Object Detection Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing Advances in Neural Information Processing Systems (NeurIPS), 2023 paper / code

	GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan International Journal of Computer Vision (IJCV), 2023 paper / code

Source code credit to Dr. Jon Barron