LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911887779692544 |
|---|---|
| author | Zhao, Qihao Dai, Yalun Li, Hao Hu, Wei Zhang, Fan Liu, Jun |
| author_facet | Zhao, Qihao Dai, Yalun Li, Hao Hu, Wei Zhang, Fan Liu, Jun |
| contents | 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 (e.g., large language models, LLMs), 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content Zhao, Qihao Dai, Yalun Li, Hao Hu, Wei Zhang, Fan Liu, Jun Computer Vision and Pattern Recognition 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 (e.g., large language models, LLMs), 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. |
| title | LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.05854 |