Lamarck 提出继承式 Adapter 专家实现无回放域增量学习
Inherited Adapter Experts for Replay-Free Domain-Incremental Learning
AI 导读
arXiv 论文提出名为 Lamarck 的无回放域增量学习方法:冻结预训练 ViT,每个新域训练一个 expert,并采用免训练 Mahalanobis router 选择 expert。
正文 · 原文
Abstract:Replay-free domain-incremental learning trains a model on the same classes in successive domains without keeping earlier images. Per-domain learners freeze a pre-trained ViT and train an additional expert for each new domain: the small set of parameters and the classification head learned on that domain. Test images carry no domain label, so a router selects one expert for each image. Recent work trains this router. However, a training-free Mahalanobis router costs the analyzed learners under 2.7 points of final accuracy relative to always selecting each image's own-domain expert. The experts, not this router, limit accuracy. Our learner, Lamarck, therefore uses this router and strengthens the experts. Its adapters, small trainable layers that correct every image token after each deep ViT block, add 4.4 points of final accuracy on the deepfake benchmark CDDB-Hard. In addition, each expert is initialized from its predecessor at no extra cost: the domains share their classes, so an image misrouted to a later expert loses less. Against twelve frozen-backbone baselines under one protocol, Lamarck is first on CDDB-Hard by 5.2 points, second on DomainNet and OfficeHome, and highest in mean accuracy.
| Comments: | 21 pages (8 pages main text, plus references and supplementary material), 8 figures, 23 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24145 [cs.CV] |
| (or arXiv:2611.24145v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24145 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gyutae Oh [view email]
[v1]
Wed, 18 Nov 2026 09:53:15 UTC (607 KB)
来源:arXiv cs.AI · arxiv.org