Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods trade-off between inference time and accuracy, ACMap consolidates task-specific adap...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an
exemplar-free framework for class-incremental learning (CIL) that addresses
both catastrophic forgetting and scalability. While existing methods trade-off
between inference time and accuracy, ACMap consolidates task-specific adapters
into a single adapter, ensuring constant inference time across tasks without
compromising accuracy. The framework employs adapter merging to build a shared
subspace that aligns task representations and mitigates forgetting, while
centroid prototype mapping maintains high accuracy through consistent
adaptation in the shared subspace. To further improve scalability, an early
stopping strategy limits adapter merging as tasks increase. Extensive
experiments on five benchmark datasets demonstrate that ACMap matches
state-of-the-art accuracy while maintaining inference time comparable to the
fastest existing methods. The code is available at
https://github.com/tf63/ACMap |
---|---|
DOI: | 10.48550/arxiv.2412.18219 |