Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or without small task overlaps, real-world scenarios often involve hierarchical relationships between old and new tasks, posing another challenge for traditional CL approaches. To address this challenge, we propose a novel multi-level hierarchical class incremental task configuration with an online learning constraint, called hierarchical label expansion (HLE). Our configuration allows a network to first learn coarse-grained classes, with data labels continually expanding to more fine-grained classes in various hierarchy depths. To tackle this new setup, we propose a rehearsal-based method that utilizes hierarchy-aware pseudo-labeling to incorporate hierarchical class information. Additionally, we propose a simple yet effective memory management and sampling strategy that selectively adopts samples of newly encountered classes. Our experiments demonstrate that our proposed method can effectively use hierarchy on our HLE setup to improve classification accuracy across all levels of hierarchies, regardless of depth and class imbalance ratio, outperforming prior state-of-the-art works by significant margins while also outperforming them on the conventional disjoint, blurry and i-Blurry CL setups.

翻译：持续学习（CL）使模型能够适应新任务和新环境，同时避免遗忘先前学到的知识。尽管当前的持续学习设定忽略了旧任务与新任务之间标签的关系（无论是否存在小规模任务重叠），但现实场景中旧任务与新任务往往存在层次化关系，这为传统持续学习方法带来了新的挑战。为解决这一挑战，我们提出了一种新颖的多层次分层类增量任务配置，并引入在线学习约束，称为分层标签扩展（HLE）。该配置允许网络先学习粗粒度类别，随后数据标签持续扩展为不同层次深度的更细粒度类别。为应对这一新设定，我们提出了一种基于经验回放的方法，通过层次感知伪标签技术融合分层类别信息。此外，我们设计了一种简单高效的记忆管理与采样策略，可选择性地采纳新出现类别的样本。实验表明，所提方法能有效利用HLE设定中的层次结构，在不同深度和类别不平衡比条件下，提升所有层级上的分类准确率，在显著优于先前最先进工作的同时，在传统离散型、模糊型和i-Blurry型持续学习设定中亦表现出色。