Class-incremental learning (CIL) aims to train classifiers that learn new classes without forgetting old ones. Most CIL methods focus on balanced data distribution for each task, overlooking real-world long-tailed distributions. Therefore, Long-Tailed Class-Incremental Learning (LT-CIL) has been introduced, which trains on data where head classes have more samples than tail classes. Existing methods mainly focus on preserving representative samples from previous classes to combat catastrophic forgetting. Recently, dynamic network algorithms frozen old network structures and expanded new ones, achieving significant performance. However, with the introduction of the long-tail problem, merely extending task-specific parameters can lead to miscalibrated predictions, while expanding the entire model results in an explosion of memory size. To address these issues, we introduce a novel Task-aware Expandable (TaE) framework, dynamically allocating and updating task-specific trainable parameters to learn diverse representations from each incremental task, while resisting forgetting through the majority of frozen model parameters. To further encourage the class-specific feature representation, we develop a Centroid-Enhanced (CEd) method to guide the update of these task-aware parameters. This approach is designed to adaptively minimize the distances between intra-class features while simultaneously maximizing the distances between inter-class features across all seen classes. The utility of this centroid-enhanced method extends to all "training from scratch" CIL algorithms. Extensive experiments were conducted on CIFAR-100 and ImageNet100 under different settings, which demonstrates that TaE achieves state-of-the-art performance.

翻译：类别增量学习（CIL）旨在训练能够学习新类别而不遗忘旧类别的分类器。大多数CIL方法关注每个任务的平衡数据分布，忽视了现实世界中的长尾分布。因此，长尾类别增量学习（LT-CIL）被引入，它在头部类样本数多于尾部类的数据上进行训练。现有方法主要致力于保留旧类别的代表性样本以对抗灾难性遗忘。近年来，动态网络算法冻结旧网络结构并扩展新网络，取得了显著性能。然而，随着长尾问题的引入，仅扩展任务特定参数可能导致预测校准失调，而扩展整个模型则会导致内存空间爆炸。为解决这些问题，我们提出了一个新颖的任务感知可扩展（TaE）框架，动态分配和更新任务特定的可训练参数，以从每个增量任务中学习多样化的表示，同时通过冻结大部分模型参数来抵抗遗忘。为进一步促进类别特定特征表示，我们开发了一种质心增强（CEd）方法，用于指导这些任务感知参数的更新。该方法旨在自适应地最小化类内特征之间的距离，同时最大化所有已见类别中类间特征之间的距离。这种质心增强方法可适用于所有“从头训练”的CIL算法。我们在CIFAR-100和ImageNet100的不同设置下进行了大量实验，结果表明TaE达到了最先进的性能。