用生成图文缓解遗忘，无需存储真实数据。
Caption, Create, Continue: Continual Learning with Pre-trained Generative Vision-Language Models
- 用BLIP和稳定扩散生成图文，替代真实数据
- 在三个数据集上平均准确率提升54%
- 内存效率比基线高63倍，适合资源受限场景
持续学习（CL）使模型能适应不断变化的数据流而避免灾难性遗忘，是现实AI系统的基本需求。然而现有方法通常依赖大型回放缓冲区或大量标注数据，因存储、隐私和成本限制难以实用。我们提出CLTS（基于文本-图像协同的持续学习），一种新型类增量框架，无需存储真实任务数据即可缓解遗忘。CLTS利用预训练视觉语言模型：用BLIP生成图像描述，用稳定扩散生成样本。每个任务由专用任务头处理，任务路由器通过生成数据判断输入应分配至哪个任务头。在三个基准数据集上，CLTS将平均任务准确率提升最高达54%，内存效率较四种近期基线高出63倍，证明其具备更强的记忆保持与适应能力。该方法通过引入生成式图文增强，为可扩展持续学习提供了新视角。
原文摘要 · Abstract (English)
Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current methods often depend on large replay buffers or heavily annotated datasets which are impractical due to storage, privacy, and cost constraints. We propose CLTS (Continual Learning via Text-Image Synergy), a novel class-incremental framework that mitigates forgetting without storing real task data. CLTS leverages pre-trained vision-language models, BLIP (Bootstrapping Language-Image Pre-training) for caption generation and stable diffusion for sample generation. Each task is handled by a dedicated Task Head, while a Task Router learns to assign inputs to the correct Task Head using the generated data. On three benchmark datasets, CLTS improves average task accuracy by up to 54% and achieves 63 times better memory efficiency compared to four recent continual learning baselines, demonstrating improved retention and adaptability. CLTS introduces a novel perspective by integrating generative text-image augmentation for scalable continual learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。