CLoG：图像生成模型持续学习的基准测试
CLoG: Benchmarking Continual Learning of Image Generation Models
AI总结：
本文提出将持续学习研究从分类任务转向生成模型持续学习（CLoG），系统分析其独特挑战，适配三类现有CL方法并构建多样化基准，为终身学习范式下的AIGC发展提供支撑。
摘要：
持续学习（CL）在人工智能中构成一项重大挑战，旨在模拟人类逐步获取知识与技能的能力。尽管大量研究集中于分类任务背景下的持续学习，但日益强大的生成模型的出现使得探索生成模型持续学习（CLoG）成为必要。本文倡导将研究重点从基于分类的持续学习转向CLoG。我们系统地识别了CLoG相较于传统基于分类的持续学习所带来的独特挑战。我们将三类现有的持续学习方法——基于回放的方法、基于正则化的方法和基于参数隔离的方法——适配到生成任务中，并引入了具有高度多样性和广泛任务覆盖范围的CLoG综合基准。我们的基准和结果产生了有趣的见解，这些见解对开发未来的CLoG方法具有重要价值。此外，我们将公开发布一个代码库，旨在促进CLoG中的便捷基准测试和实验，地址为https://github.com/linhaowei1/CLoG。我们相信，将研究重点转向CLoG将使持续学习社区受益，并为终身学习范式下的下一代人工智能生成内容（AIGC）指明道路。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
