pith. sign in

Foster: Feature boosting and compression for class-incremental learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Memory-Efficient Continual Learning with CLIP Models

cs.LG · 2026-05-05 · unverdicted · novelty 5.0

A per-class loss reweighting scheme based on distributional robustness allows CLIP models to perform class-incremental and domain-incremental learning with minimal memory while limiting forgetting on CIFAR-100, ImageNet1K, and DomainNet.

citing papers explorer

Showing 1 of 1 citing paper.

  • Memory-Efficient Continual Learning with CLIP Models cs.LG · 2026-05-05 · unverdicted · none · ref 16

    A per-class loss reweighting scheme based on distributional robustness allows CLIP models to perform class-incremental and domain-incremental learning with minimal memory while limiting forgetting on CIFAR-100, ImageNet1K, and DomainNet.