FETCH：一种用于图像分类持续学习的内存高效回放方法
FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification
AI总结：
FETCH提出两阶段压缩回放方法，在GDumb流程中评估压缩技术，通过预训练编码和压缩存储提高CIFAR10和CIFAR100的准确率，简单压缩优于深度自编码器。
摘要：
类增量持续学习是研究的重要领域，因为静态深度学习方法无法适应不断变化的任务和数据分布。在以往的工作中，使用回放和压缩回放技术取得了有前景的结果。在常规回放领域，GDumb取得了出色的结果，但需要大量内存。这一问题可以通过压缩回放技术来解决。本工作的目标是在GDumb的流程中评估压缩回放。我们提出了FETCH，一种两阶段压缩方法。首先，来自持续数据流的样本由预训练神经网络的早期层进行编码。其次，样本在存储到情节记忆之前被压缩。遵循GDumb，仅使用来自回放记忆的解压缩样本从头训练剩余的分类头。我们在不同场景下评估了FETCH，并表明该方法可以提高CIFAR10和CIFAR100上的准确率。在我们的实验中，简单的压缩方法（例如，张量的量化）优于深度自编码器。未来，FETCH可以作为在受限内存场景下基准测试压缩回放学习的基线。
英文摘要：
Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, promising results were achieved using replay and compressed replay techniques. In the field of regular replay, GDumb achieved outstanding results but requires a large amount of memory. This problem can be addressed by compressed replay techniques. The goal of this work is to evaluate compressed replay in the pipeline of GDumb. We propose FETCH, a two-stage compression approach. First, the samples from the continual datastream are encoded by the early layers of a pre-trained neural network. Second, the samples are compressed before being stored in the episodic memory. Following GDumb, the remaining classification head is trained from scratch using only the decompressed samples from the reply memory. We evaluate FETCH in different scenarios and show that this approach can increase accuracy on CIFAR10 and CIFAR100. In our experiments, simple compression methods (e.g., quantization of tensors) outperform deep autoencoders. In the future, FETCH could serve as a baseline for benchmarking compressed replay learning in constrained memory scenarios.
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。
