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.
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 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
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.