arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.04485cs.CVcs.LG
收藏

一种用于增量学习的记忆Transformer网络

A Memory Transformer Network for Incremental Learning

Google Research(谷歌研究院);University College London(伦敦大学学院)

Ahmet Iscen, Thomas Bird, Mathilde Caron, Alireza Fathi, Cordelia Schmid

摘要:

我们研究了类增量学习,这是一种训练设置,其中随着时间的推移观察新的数据类,以便模型从中学习。尽管简单的问题制定,天真的分类模型的应用,类增量学习的结果在“灾难性遗忘“以前看到的类。最成功的现有方法之一是使用样本的存储器,其通过将过去数据的子集保存到存储体中并在训练未来任务时利用它来防止遗忘,从而克服了灾难性遗忘的问题。在我们的论文中,我们建议提高这个存储体的利用率:我们不仅使用它作为额外的训练数据的来源,像现有的作品,但也集成在预测过程中明确。我们的方法,记忆Transformer网络(MTN),学习如何结合和聚合的信息,从最近的邻居在内存中的Transformer,使更准确的预测。我们进行了大量的实验和消融来评估我们的方法。我们证明了MTN在具有挑战性的ImageNet-1 k和Google-Landmarks-1 k增量学习基准测试中达到了最先进的性能。

英文摘要:

We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks. In our paper, we propose to enhance the utilization of this memory bank: we not only use it as a source of additional training data like existing works but also integrate it in the prediction process explicitly.Our method, the Memory Transformer Network (MTN), learns how to combine and aggregate the information from the nearest neighbors in the memory with a transformer to make more accurate predictions. We conduct extensive experiments and ablations to evaluate our approach. We show that MTN achieves state-of-the-art performance on the challenging ImageNet-1k and Google-Landmarks-1k incremental learning benchmarks.

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。

↑