Class incremental learning consists in training discriminative models to
classify an increasing number of classes over time. However, doing so using
only the newly added class data leads to the known problem of catastrophic
forgetting of the previous classes. Recently, dynamic deep learning
architectures have been shown to exhibit a better stability-plasticity
trade-off by dynamically adding new feature extractors to the model in order to
learn new classes followed by a compression step to scale the model back to its
original size, thus avoiding a growing number of parameters. In this context,
we propose a new algorithm that enhances the compression of previous class
knowledge by cutting and mixing patches of previous class samples with the new
images during compression using our Rehearsal-CutMix method. We show that this
new data augmentation reduces catastrophic forgetting by specifically targeting
past class information and improving its compression. Extensive experiments
performed on the CIFAR and ImageNet datasets under diverse incremental learning
evaluation protocols demonstrate that our approach consistently outperforms the
state-of-the-art . The code will be made available upon publication of our
work.

我们提出了一种新算法，通过使用我们的 Rehearsal-CutMix 方法在压缩过程中切割和混合之前类别样本的图像补丁与新图像，来增强先前类别知识的压缩。在 CIFAR 和 ImageNet 数据集上进行的大量实验证明，我们的方法在不同的增量学习评估协议下始终优于现有技术。