I am a Ph.D. candidate at Beijing University of Chemical Technology, supervised by Prof. Fan Zhang and Prof. Wei Hu. I am currently a visiting student at VLG, Singapore University of Technology and Design, where I have been working with Prof. Jun Liu since March 2023. My research interests mainly focus on data-efficient learning/generation.

🔥 News

• 2024.04:  🏅 LTGC is selected for oral presentation at CVPR 2024 (Oral Paper Rate: 0.78% (90/11532), Acceptance Rate: 23.6% (2719/11532)).
• 2024.02:  🎉 One paper accept to CVPR 2024.
• 2023.09:  🎉 One paper accept to T-CSVT.
• 2023.09:  🌟 Invited as a reviewer for ICLR 2024.
• 2023.07:  🎉 One paper accept to ICCV 2023.

📝 Publications （* Equal Contribution）

CVPR 2024

LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content (Oral)

A generative and tuning framework leveraging the knowledge of large language models for long-tail recognition.

Qihao Zhao *, Yalun Dai *, Hao Li, Wei Hu, Fan Zhang, Jun Liu

Code

ICCV 2023

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

A long-tail learning method for maximizing expert recognition diversity with minimum model variance.

Qihao Zhao, Chen Jiang, Wei Hu, Fan Zhang, Jun Liu

Code

ICLR 2023

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

A novel data augmentation method designed for ViTs considering global information mixture and label space re-weighting.

Qihao Zhao, Yangyu Huang, Wei Hu, Fan Zhang, Jun Liu

Code

T-CSVT

OHD: An Online Category-aware Framework for Learning with Noisy Labels under Long-Tailed Distribution

A novel framework to address the challenge of noisy labels under long-tailed distribution.

Qihao Zhao, Fan Zhang, Wei Hu, Songhe Feng, Jun Liu

Code

Neural Networks

P-DIFF+: Improving Learning Classifier with Noisy Labels by Noisy Negative Learning Loss

A novel loss function, that mining knowledge from noisy samples to improve the robustness of models.

Qihao Zhao, Wei Hu, Yangyu Huang, Fan Zhang

Code

📖 Educations

• 2023.03 - Now, Singapore University of Technology and Design, Visiting student
• 2021.09 - Now, Beijing University of Chemical Technology, Ph.D. candidate
• 2019.09 - 2021.06, Beijing University of Chemical Technology, Master

💻 Service

• Reviewer: NeurIPS 2023, ICLR 2024