Pith. sign in

Gfpl: Generative federated prototype learning for resource-constrained and data-imbalanced vision task,

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

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

BPG: Balancing Plasticity and Generalization for Domain Incremental Learning

cs.CV · 2026-08-11 · conditional · novelty 6.0

BPG sizes per-domain adapters inversely to a feature-separability score and replaces hard domain selection with confidence-weighted logit fusion, setting state-of-the-art accuracy and near-zero forgetting on three domain incremental learning benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • BPG: Balancing Plasticity and Generalization for Domain Incremental Learning cs.CV · 2026-08-11 · conditional · none · ref 5

    BPG sizes per-domain adapters inversely to a feature-separability score and replaces hard domain selection with confidence-weighted logit fusion, setting state-of-the-art accuracy and near-zero forgetting on three domain incremental learning benchmarks.