DLC inserts lightweight classifier-proximal plugins into distillation-based continual learning to achieve 8% accuracy gains on large benchmarks with only 4% extra backbone parameters.
Prototype-based continual learning with label-free replay buffer and cluster 8 preservation loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
DLC inserts lightweight classifier-proximal plugins into distillation-based continual learning to achieve 8% accuracy gains on large benchmarks with only 4% extra backbone parameters.