Skip to main content
Search

# Domain Incremental Learning

2 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.

  2. arXiv

    Frozen time-series foundation models can follow recurring conditions: PACT edits only embeddings and holds macro-F1 above 0.95 on a four-condition bearing stream

    When operating conditions recur, adapting a time-series foundation model by global fine-tuning changes parameters shared across conditions and degrades earlier ones. PACT partitions the frozen source embedding space into local regions, learns a lightweight residual correction only in the regions affected by each new condition, and keeps an explicit identity path that a learned gate softly selects among at inference. On a four-condition bearing-fault stream, using 5% labeled calibration data per arriving condition and no condition identity at test time, average macro-F1 stays above 0.95.

You’re all caught up