Pith. sign in

Few- shot class-incremental learning via relation knowledge distillation,

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

1 Pith paper citing it

citation-role summary

method 1

citation-polarity summary

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

roles

method 1

polarities

support 1

representative citing papers

On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning

cs.LG · 2024-12-15 · conditional · novelty 5.0

Displacement Knowledge Distillation matches the distribution of feature differences between teacher and student, and a dual distillation network applies it to novel classes in few-shot class-incremental learning, achieving state-of-the-art retention on CIFAR-100, miniImageNet, and CUB-200.

citing papers explorer

Showing 1 of 1 citing paper.

  • On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning cs.LG · 2024-12-15 · conditional · none · ref 8

    Displacement Knowledge Distillation matches the distribution of feature differences between teacher and student, and a dual distillation network applies it to novel classes in few-shot class-incremental learning, achieving state-of-the-art retention on CIFAR-100, miniImageNet, and CUB-200.