Today, the IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）announced the acceptance results and the research group of Prof. Fan Zhang from our institute had a paper selected.
Paper Information: Qihao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu: “LTGC: Long-Tail Recognition via Leveraging Generated Content”
Abstract: Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models, LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), organized by IEEE, is one of the world's leading academic conferences in the field of computer science, and is rated as the top tier academic conference by the China Computer Federation (CCF-A). CVPR is ranked 4th among all academic journals/conferences by Google Scholar's conference impact rankings of academic journals/conferences published in 2024.
The first author of the paper is Qihao Zhao, a PhD student of the School of Information Science and Technology, and the co-first author and second author are the 18th grade undergraduates of the School of Information Science and Technology, Yalun Dai and Hao Li, under the supervision of Prof. Fan Zhang and Associate Prof. Wei Hu, and in collaboration with the Singapore University of Technology and Design (SUTD), with the Beijing University of Chemical Technology as the first completing institution. This work was supported by the National Natural Science Foundation of China and others.