Zhou Da-Wei, Wang Qi-Wei, Qi Zhi-Hong, Ye Han-Jia, Zhan De-Chuan, Liu Ziwei
IEEE Trans Pattern Anal Mach Intell. 2024 Dec;46(12):9851-9873. doi: 10.1109/TPAMI.2024.3429383. Epub 2024 Nov 6.
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs - the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in class-incremental learning and summarize these methods from several aspects. We also provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures.
深度模型，例如卷积神经网络（CNNs）和视觉Transformer，在封闭世界中的许多视觉任务中都取得了令人瞩目的成就。然而，在我们不断变化的世界中，新的类别不时出现，这就要求学习系统不断获取新知识。类别增量学习（CIL）使学习者能够逐步纳入新类别的知识，并在所有已见类别中构建一个通用分类器。相应地，当直接用新类别的实例训练模型时，会出现一个致命问题——模型往往会灾难性地忘记先前类别的特征，其性能会急剧下降。机器学习社区已经做出了许多努力来解决灾难性遗忘问题。在本文中，我们全面综述了类别增量学习的最新进展，并从几个方面总结了这些方法。我们还在基准图像分类任务中对17种方法进行了严格统一的评估，以实证地找出不同算法的特点。此外，我们注意到当前的比较协议忽略了模型存储中内存预算的影响，这可能导致不公平的比较和有偏差的结果。因此，我们主张通过在评估中对齐内存预算以及一些与内存无关的性能度量来进行公平比较。
