AI Paper Atlas

Research map / Continual learning / Class-incremental

Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay

Huan Liu, Li Gu, Zhixiang Chi, Yang Wang, Yuanhao Yu, Jun Chen, Jin Tang

ECCV 2022 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 118 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add entropy regularization to generator training (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILaverage accuracy: 60.39 -> 60.77Improved
add entropy regularization to generator training (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILfinal session accuracy: 49.50 -> 50.14Improved
add re-labeling of generated data with one-hot labels (instead of KL distillation) (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILaverage accuracy: 59.74 -> 60.77Improved
add re-labeling of generated data with one-hot labels (instead of KL distillation) (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILfinal session accuracy: 48.92 -> 50.14Improved
add backbone fine-tuning during incremental sessions (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILaverage accuracy: 59.90 -> 60.77Improved
add backbone fine-tuning during incremental sessions (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILfinal session accuracy: 49.13 -> 50.14Improved
replace DeepInversion replay with entropy-regularized generator replay (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILaverage accuracy: 59.11 -> 60.77Improved
replace DeepInversion replay with entropy-regularized generator replay (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILfinal session accuracy: 48.48 -> 50.14Improved
add re-labeling and backbone fine-tuning to DeepInversion replay (ablation)DeepInversion · CIFAR-100 FSCILaverage accuracy: 57.92 -> 59.11Improved
use replayed data (iCaRL*, NCM* re-implementations) instead of TOPIC without replayNCM · CIFAR-100 FSCILaverage accuracy: 42.62 -> 58.60Improved
replay data quantity different from training data size (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILaverage accuracyHurt
use entropy regularization in generator on label distribution (ablation)Entropy-regularized data-free replay · CIFAR-100 FSCILshare of generated samples from few-shot classesImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy