CLoG: Benchmarking Continual Learning of Image Generation Models
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_ | 1866914829312196608 |
|---|---|
| author | Zhang, Haotian Zhou, Junting Lin, Haowei Ye, Hang Zhu, Jianhua Wang, Zihao Gao, Liangcai Wang, Yizhou Liang, Yitao |
| author_facet | Zhang, Haotian Zhou, Junting Lin, Haowei Ye, Hang Zhu, Jianhua Wang, Zihao Gao, Liangcai Wang, Yizhou Liang, Yitao |
| contents | Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of classification tasks, the advent of increasingly powerful generative models necessitates the exploration of Continual Learning of Generative models (CLoG). This paper advocates for shifting the research focus from classification-based CL to CLoG. We systematically identify the unique challenges presented by CLoG compared to traditional classification-based CL. We adapt three types of existing CL methodologies, replay-based, regularization-based, and parameter-isolation-based methods to generative tasks and introduce comprehensive benchmarks for CLoG that feature great diversity and broad task coverage. Our benchmarks and results yield intriguing insights that can be valuable for developing future CLoG methods. Additionally, we will release a codebase designed to facilitate easy benchmarking and experimentation in CLoG publicly at https://github.com/linhaowei1/CLoG. We believe that shifting the research focus to CLoG will benefit the continual learning community and illuminate the path for next-generation AI-generated content (AIGC) in a lifelong learning paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04584 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CLoG: Benchmarking Continual Learning of Image Generation Models Zhang, Haotian Zhou, Junting Lin, Haowei Ye, Hang Zhu, Jianhua Wang, Zihao Gao, Liangcai Wang, Yizhou Liang, Yitao Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of classification tasks, the advent of increasingly powerful generative models necessitates the exploration of Continual Learning of Generative models (CLoG). This paper advocates for shifting the research focus from classification-based CL to CLoG. We systematically identify the unique challenges presented by CLoG compared to traditional classification-based CL. We adapt three types of existing CL methodologies, replay-based, regularization-based, and parameter-isolation-based methods to generative tasks and introduce comprehensive benchmarks for CLoG that feature great diversity and broad task coverage. Our benchmarks and results yield intriguing insights that can be valuable for developing future CLoG methods. Additionally, we will release a codebase designed to facilitate easy benchmarking and experimentation in CLoG publicly at https://github.com/linhaowei1/CLoG. We believe that shifting the research focus to CLoG will benefit the continual learning community and illuminate the path for next-generation AI-generated content (AIGC) in a lifelong learning paradigm. |
| title | CLoG: Benchmarking Continual Learning of Image Generation Models |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.04584 |