使用扩散模型进行蒸馏和回放的类增量学习
Class-Incremental Learning using Diffusion Model for Distillation and Replay
AI总结：
利用预训练Stable Diffusion生成合成样本，用于蒸馏和回放，提升大规模类增量学习性能。
摘要：
类增量学习旨在以增量方式学习新类别，同时不遗忘先前学到的类别。多项研究工作表明，增量模型可以利用额外数据来帮助缓解灾难性遗忘。在本工作中，我们借鉴文本到图像生成模型的最新突破及其广泛分布，提出使用预训练的Stable Diffusion模型作为类增量学习的额外数据来源。与依赖外部（通常是无标签的）真实图像数据集的竞争方法相比，我们的方法可以生成与先前遇到的图像属于相同类别的合成样本。这使得我们不仅可以在蒸馏损失中使用这些额外数据样本，还可以在分类损失的回放中使用它们。在竞争性基准CIFAR100、ImageNet-Subset和ImageNet上的实验表明，这种新方法可以用于进一步提升大规模数据集上最先进的类增量学习方法的性能。
英文摘要：
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate catastrophic forgetting. In this work, following the recent breakthrough in text-to-image generative models and their wide distribution, we propose the use of a pretrained Stable Diffusion model as a source of additional data for class-incremental learning. Compared to competitive methods that rely on external, often unlabeled, datasets of real images, our approach can generate synthetic samples belonging to the same classes as the previously encountered images. This allows us to use those additional data samples not only in the distillation loss but also for replay in the classification loss. Experiments on the competitive benchmarks CIFAR100, ImageNet-Subset, and ImageNet demonstrate how this new approach can be used to further improve the performance of state-of-the-art methods for class-incremental learning on large scale datasets.
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。
