论文标题
具有强大的预训练模型的课堂学习
Class-Incremental Learning with Strong Pre-trained Models
论文作者
论文摘要
在从少量类（基类）开始的情况下，已经广泛研究了课堂学习学习（CIL）。取而代之的是，我们探索了一个研究不足的CIL现实环境设置，该设置是从在大量基类中进行预训练的强大模型开始。我们假设强大的基本模型可以为新颖的类别提供良好的表示，并且可以通过少量适应来进行增量学习。我们提出了一个2阶段的训练方案，i）功能增强 - 将部分的克隆部分克隆并在新型数据上进行微调，ii）融合 - 将基础和新型分类器组合到统一的分类器中。实验表明，所提出的方法在大型成像网数据集上的最先进的CIL方法明显胜过最先进的CIL方法（例如，总体准确性比最佳的10％）。我们还提出和分析了研究的实际CIL方案，例如基本 - 新颖的与分配变化重叠。我们提出的方法是鲁棒的，并概括了所有分析的CIL设置。 代码可在https://github.com/amazon-research/sp-cil上找到。
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.
