In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this problem have updated both the classification head and the feature extractor body at each session of CIL. In this work, we develop a baseline method, First Session Adaptation (FSA), that sheds light on the efficacy of existing CIL approaches and allows us to assess the relative performance contributions from head and body adaption. FSA adapts a pre-trained neural network body only on the first learning session and fixes it thereafter; a head based on linear discriminant analysis (LDA), is then placed on top of the adapted body, allowing exact updates through CIL. FSA is replay-free i.e.~it does not memorize examples from previous sessions of continual learning. To empirically motivate FSA, we first consider a diverse selection of 22 image-classification datasets, evaluating different heads and body adaptation techniques in high/low-shot offline settings. We find that the LDA head performs well and supports CIL out-of-the-box. We also find that Featurewise Layer Modulation (FiLM) adapters are highly effective in the few-shot setting, and full-body adaption in the high-shot setting. Second, we empirically investigate various CIL settings including high-shot CIL and few-shot CIL, including settings that have previously been used in the literature. We show that FSA significantly improves over the state-of-the-art in 15 of the 16 settings considered. FSA with FiLM adapters is especially performant in the few-shot setting. These results indicate that current approaches to continuous body adaptation are not working as expected. Finally, we propose a measure that can be applied to a set of unlabelled inputs which is predictive of the benefits of body adaptation.

翻译：在类增量学习（Class-Incremental Learning, CIL）中，图像分类系统在每个学习会话中会遇到新类别，并需增量式更新。现有方法在每个CIL会话中同时更新分类头和特征提取器主体。本文提出了一种基线方法——首次会话适应（First Session Adaptation, FSA），该方法揭示了现有CIL方法的有效性，并使我们能够评估头与主体适应的相对性能贡献。FSA仅在第一次学习会话中适应预训练的神经网络主体后固定不变；随后在适应后的主体之上放置基于线性判别分析（Linear Discriminant Analysis, LDA）的分类头，从而实现CIL期间的精确更新。FSA无需重放（即不记忆先前连续学习会话中的样本）。为实证验证FSA，我们首先选取了22个多样化的图像分类数据集，在不同样本量（高/低样本）的离线场景下评估了不同分类头与主体适应技术。我们发现LDA头性能优异，且可直接支持CIL；此外，特征层调制（Featurewise Layer Modulation, FiLM）适配器在小样本场景下高度有效，而全主体适应在大样本场景下表现更佳。其次，我们实证研究了多种CIL设置，包括高样本CIL和小样本CIL（含文献中曾使用的设置）。结果表明，在16种设置中，FSA在15种上显著优于当前最优方法。其中，采用FiLM适配器的FSA在小样本场景下尤为高效。这些结果表明，现有的连续主体适应方法未达到预期效果。最后，我们提出了一种可应用于未标注输入集的度量指标，该指标能够预测主体适应的收益。