XIL: Cross-Expanding Incremental Learning

Heayoun Choi, Hyundong Jin, Eunwoo Kim

Keywords: Class-incremental learning, Continual learning, Image Classification

Abstract:

Class-Incremental Learning (CIL) traditionally assumes that all tasks share a similar domain distribution, limiting its applicability in real-world scenarios where data arrive from evolving environments.
We introduce a new problem setting, Cross-Expanding Incremental Learning (XIL), which extends CIL by requiring models to handle class-incremental data across distinct domains and to expand class-domain associations bidirectionally.
In this setting, new classes should be integrated into previously seen domains, while earlier classes are extended to newly encountered ones, a capability we refer to as bidirectional domain transferability (BiDoT).
To address XIL, we present a new framework, Semantic Expansion through Evolving Domains (XEED), which leverages domain-specialized prompts, residual-guided representation modulation, and evolving prototype embeddings to expand class semantics across previously encountered domains.
We further introduce the BiDoT Score, a novel metric for quantifying the degree of BiDoT.
Extensive experiments on benchmark datasets with significant domain shifts demonstrate that XEED outperforms existing CIL baselines by a large margin in both standard accuracy and BiDoT scores, establishing a strong foundation for realistic continual learning under domain-evolving conditions.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 10066