Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time for each test sample. Predicting the task-id for each test sample is a challenging problem. An emerging theoretically justified and effective approach is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with forgetting. The model for each task in this approach is an out-of-distribution (OOD) detector rather than a conventional classifier. The OOD detector can perform both within-task (in-distribution (IND)) class prediction and OOD detection. The OOD detection capability is the key for task-id prediction during inference for each test sample. However, this paper argues that using a traditional OOD detector for task-id prediction is sub-optimal because additional information (e.g., the replay data and the learned tasks) available in CIL can be exploited to design a better and principled method for task-id prediction. We call the new method TPLR (Task-id Prediction based on Likelihood Ratio}). TPLR markedly outperforms strong CIL baselines.

翻译：类增量学习(CIL)是持续学习中具有挑战性的场景，需要顺序学习一系列任务。每个任务包含一组独立的类别。CIL的关键特征在于测试时不为每个测试样本提供任务标识符(或任务ID)。为每个测试样本预测任务ID是一个具有挑战性的问题。一种新兴的、经理论验证且有效的方法是：基于任务增量学习(TIL)方法，在共享网络中为每个任务训练专用模型以应对遗忘。该方法的每个任务模型本质上是分布外(OOD)检测器，而非传统分类器。OOD检测器既能执行任务内(分布内(IND))类别预测，也能进行OOD检测。对于测试样本的推理过程，OOD检测能力是实现任务ID预测的关键。然而，本文认为使用传统OOD检测器进行任务ID预测存在次优性，因为CIL中可利用的额外信息(例如回放数据和已学习任务)可用于设计更优且原则性的任务ID预测方法。我们将新方法命名为TPLR(基于似然比的任务ID预测)。该方法显著优于强基准CIL方法。