Skip to main content
Search

# Adapter Experts

1 related articles

Subscribe to updates
  1. arXiv

    No old images, still learning new domains: Lamarck inherits each expert from the last and leads CDDB-Hard by 5.2 points

    In replay-free domain-incremental learning, test images carry no domain label, so a router picks one per-domain expert for each image. Lamarck keeps a training-free Mahalanobis router and spends its effort on the experts: an adapter after each deep ViT block corrects every image token, and each expert, adapters included, is initialized from its predecessor. On CDDB-Hard the adapters add 4.36 ACC points over prompt-only experts, and the full learner beats the best of twelve frozen-backbone baselines by 5.18 points while posting the highest mean accuracy across three benchmarks.

You’re all caught up