Lihe Yang

I am a second-year PhD student at The University of Hong Kong, fortunately supervised by Prof. Hengshuang Zhao.

I received my Bachelor and Master degree from Nanjing University in 2020 and 2023 respectively, fortunately supervised by Prof. Yinghuan Shi.

My current research focuses on vision foundation model, vision-language model, and data-centric AI.

Email / Google Scholar / GitHub

News

2025-01: UniMatch V2 is accepted by TPAMI.

2024-12: I am awarded the 2024 ByteDance Scholarship.

2024-09: Depth Anything is selected as the 5th most influential paper in CVPR 2024.

2024-09: Depth Anything V2 is accepted by NeurIPS 2024 and integrated into Apple Core ML Models.

2024-02: Depth Anything is accepted by CVPR 2024.

2023-09: One paper on generative perception is accepted by NeurIPS 2023.

2023-09: I start at HKU as a PhD student.

---- show more ----

Selected Publications

	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation Lihe Yang, Zhen Zhao, Hengshuang Zhao IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 Paper / Code
	Depth Anything V2 Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao Conference on Neural Information Processing Systems (NeurIPS), 2024 Page / Paper / Code / Demo / Media
	Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao Conference on Computer Vision and Pattern Recognition (CVPR), 2024 Most Influential Papers / Best Demo Honorable Mention Page / Paper / Code / Demo / Media
	FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models Lihe Yang, Xiaogang Xu, Bingyi Kang, Yinghuan Shi, Hengshuang Zhao Conference on Neural Information Processing Systems (NeurIPS), 2023 Paper / Code / Zhihu
	Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning Lihe Yang, Zhen Zhao, Lei Qi, Yu Qiao, Yinghuan Shi, Hengshuang Zhao International Conference on Computer Vision (ICCV), 2023 Paper / Code / Zhihu
	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, Yinghuan Shi Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Paper / Code / Zhihu
	ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Paper / Code / Zhihu
	Mining Latent Classes for Few-shot Segmentation Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao International Conference on Computer Vision (ICCV), 2021 (Oral) Paper / Code

Selected Honors

ByteDance Scholarship (15 recipients from China and Singapore), ByteDance, 2024

CVPR Best Demo Honorable Mention, CVPR, 2024

NeurIPS Top Reviewer, NeurIPS, 2023

HKU Presidential PhD Scholarship, The University of Hong Kong, 2023-2027

National Scholarship, Ministry of Education of P.R. China, 2021

Contests

1st Place, SenseTime Remote Sensing Change Detection Competition, 30,000 RMB Bonus, 2020

2nd Place, The 8th CCF BDCI Remote Sensing Image Segmentation, 20,000 RMB Bonus, 2020

2nd Place, Off Road Image Segmentation Challenge, 200,000 Yen Bonus, 2020

2nd Place, BAAI Ultra-high Resolution EM Images Segmentation, 10,000 RMB Bonus, 2019

Academic Services

Conference reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, etc.

Journal reviewer: TPAMI, TIP, TNNLS, etc.

Website Template