Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning ability, while being able to reject unknown samples that are drawn from different distributions of the learned classes. This capability is crucial to the safety of deploying CIL models in open worlds. However, despite remarkable advancements in the respective CIL and OOD detection, there lacks a systematic and large-scale benchmark to assess the capability of advanced CIL models in detecting OOD samples. To fill this gap, in this study we design a comprehensive empirical study to establish such a benchmark, named $\textbf{OpenCIL}$. To this end, we propose two principled frameworks for enabling four representative CIL models with 15 diverse OOD detection methods, resulting in 60 baseline models for OOD detection in CIL. The empirical evaluation is performed on two popular CIL datasets with six commonly-used OOD datasets. One key observation we find through our comprehensive evaluation is that the CIL models can be severely biased towards the OOD samples and newly added classes when they are exposed to open environments. Motivated by this, we further propose a new baseline for OOD detection in CIL, namely Bi-directional Energy Regularization ($\textbf{BER}$), which is specially designed to mitigate these two biases in different CIL models by having energy regularization on both old and new classes. Its superior performance is justified in our experiments. All codes and datasets are open-source at $https://github.com/mala-lab/OpenCIL$.

翻译：类增量学习（CIL）旨在训练一个模型，使其不仅能逐步适应新类别，还能保持对已学旧类别的知识。CIL中的分布外（OOD）检测则要求在保持这种增量学习能力的同时，能够拒绝来自已学类别分布之外的未知样本。这种能力对于在开放世界中安全部署CIL模型至关重要。然而，尽管CIL和OOD检测各自领域均取得了显著进展，目前仍缺乏系统化、大规模的基准来评估先进CIL模型检测OOD样本的能力。为填补这一空白，本研究设计了一项综合性实证研究以建立名为$\textbf{OpenCIL}$的基准。为此，我们提出两个原则性框架，将15种不同的OOD检测方法适配到四种代表性CIL模型中，构建出60个用于CIL中OOD检测的基线模型。实证评估在两个主流CIL数据集和六个常用OOD数据集上进行。通过全面评估，我们发现一个关键现象：当CIL模型暴露于开放环境时，可能对OOD样本和新添加类别产生严重偏差。受此启发，我们进一步提出一种新的CIL中OOD检测基线方法——双向能量正则化（$\textbf{BER}$），该方法通过对新旧类别同时施加能量正则化，专门设计用于缓解不同CIL模型中的这两种偏差。实验结果表明其具有优越性能。所有代码与数据集已在$https://github.com/mala-lab/OpenCIL$开源。