Back to AI News
arxiv

Inherited Adapter Experts for Replay-Free Domain-Incremental Learning

The paper introduces Lamarck, a replay-free domain-incremental learning method that freezes a pre-trained ViT and trains per-domain adapter experts, using a training-free Mahalanobis router to select one expert per test image. It argues that the experts, not the router, limit accuracy, and strengthens them with adapters that correct every image token after each deep ViT block. Each expert is initialized from its predecessor at no extra cost because domains share their classes. Against twelve frozen-backbone baselines under one protocol, Lamarck reports first on CDDB-Hard by 5.2 points, second on DomainNet and OfficeHome, and the highest mean accuracy.

AI Brief

It presents a concrete method and benchmark comparisons for improving replay-free domain-incremental learning without storing earlier images.

arXiv:2611.24145v1 Announce Type: cross 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!