Online Continual Learning on Hierarchical Label Expansion

TL;DR

This paper introduces a hierarchical label expansion setup for online continual learning, enabling models to learn from coarse to fine-grained classes while effectively managing memory and hierarchy information.

Contribution

It proposes a novel hierarchical class incremental task configuration with an online learning constraint and a hierarchy-aware rehearsal method for improved continual learning.

Findings

Effective use of hierarchy improves classification accuracy across all levels.

Outperforms state-of-the-art methods on hierarchical and conventional CL setups.

Robust to class imbalance and hierarchy depth.

Abstract

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.