No AI summary available for this article.
Why It Matters
Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while preserving the ability to recognize all seen classes.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while preserving the ability to recognize all seen classes. Recently, pretrained-model-based approaches have become prevalent by adapting a frozen backbone with additional lightweight trainable modules. Existing methods, however, exhibit limitations: task-specific adapters learn explicit per-task representations but are parameter- and computation-inefficient, while LoRA-based merging methods combine per-task LoRA parameters into a single model whose st...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.31096v1 · Indexed about 1 hour ago