Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation -- cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion -- combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings. Code is available at https://github.com/amazon-research/sp-cil.
翻译:在从少数班级(基础班)开始的环境下,对课堂入门学习(CIL)进行了广泛的研究。相反,我们探索了一个研究不足的CIL现实世界设置,首先是在大量基础班上经过高级培训的强大模型。我们假设一个强大的基础模型能够为新班提供良好的代表性,而渐进学习则可以通过小的适应来完成。我们提议了一个阶段培训计划,一)特征增强 -- -- 脊柱的克隆部分,并根据新数据对其进行微调;二)聚合 -- -- 将基础和新颖的分类器合并成统一的分类器。实验显示,拟议的方法大大优于大型图像网络数据集的CIL最新方法(例如,+10%的总体精确度比最佳的精确度)。我们还提议并分析未经充分研究的实用的CIL假想,例如基础-螺旋与分布变化的重叠。我们提出的方法对所有经过分析的CIL设置是稳健和笼统的。代码可在 https://github.com/amazon-resear-spy-sprial-spyc.