Replay to Remember (R2R)：一种基于生成回放的、由不确定性驱动的高效无监督持续学习框架
Replay to Remember (R2R): An Efficient Uncertainty-driven Unsupervised Continual Learning Framework Using Generative Replay
AI总结：
本文提出R2R无监督持续学习框架，通过簇级不确定性反馈和生成回放机制在多个数据集上显著提升知识保留能力并取得领先性能。
摘要：
持续学习要求神经网络在从新数据中逐步获取知识的同时保留先前已获得的知识，从而缓解“灾难性遗忘”。本文提出了一种新颖的、由不确定性驱动的无监督持续学习框架，该框架使用生成回放机制，命名为“Replay to Remember (R2R)”。所提出的R2R架构通过簇级不确定性驱动的反馈机制和由视觉语言模型（VLM）驱动的生成回放模块，以均衡比例高效利用未标注数据和合成的有标注数据。与依赖预训练模型和伪标签的传统记忆缓冲区方法不同，我们的R2R框架无需任何预先训练即可运行。它利用未标注数据的视觉特征，并通过基于聚类的不确定性估计结合动态阈值进行持续自适应。同时，生成回放机制与由DeepSeek-R1驱动的CLIP视觉语言模型共同生成代表过去经验的有标注合成数据，类似于生物视觉思维通过回放记忆来记忆并在新的、未见过的任务中采取行动。我们在CIFAR-10、CIFAR-100、CINIC-10、SVHN和TinyImageNet数据集上进行了广泛的实验分析。我们提出的R2R方法改善了知识保留能力，分别达到了98.13%、73.06%、93.41%、95.18%和59.74%的最先进性能，超过现有最先进性能4.36%以上。
英文摘要：
Continual Learning entails progressively acquiring knowledge from new data while retaining previously acquired knowledge, thereby mitigating ``Catastrophic Forgetting'' in neural networks. Our work presents a novel uncertainty-driven Unsupervised Continual Learning framework using Generative Replay, namely ``Replay to Remember (R2R)''. The proposed R2R architecture efficiently uses unlabelled and synthetic labelled data in a balanced proportion using a cluster-level uncertainty-driven feedback mechanism and a VLM-powered generative replay module. Unlike traditional memory-buffer methods that depend on pretrained models and pseudo-labels, our R2R framework operates without any prior training. It leverages visual features from unlabeled data and adapts continuously using clustering-based uncertainty estimation coupled with dynamic thresholding. Concurrently, a generative replay mechanism along with DeepSeek-R1 powered CLIP VLM produces labelled synthetic data representative of past experiences, resembling biological visual thinking that replays memory to remember and act in new, unseen tasks. Extensive experimental analyses are carried out in CIFAR-10, CIFAR-100, CINIC-10, SVHN and TinyImageNet datasets. Our proposed R2R approach improves knowledge retention, achieving a state-of-the-art performance of 98.13%, 73.06%, 93.41%, 95.18%, 59.74%, respectively, surpassing state-of-the-art performance by over 4.36%.
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。
