AI Paper Atlas

Research map / Continual learning / Class-incremental

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

James Smith, Yen-Chang Hsu, Jonathan Balloch, Yilin Shen, Hongxia Jin, Zsolt Kira

ICCV 2021 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 180 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 task balancing loss weighting (ablation)Ours · CIFAR-100 (10 tasks, ablation)final accuracy A_N (%): 23.4 -> 33.7Improved
use modified cross-entropy loss instead of standard CE (ablation)Ours · CIFAR-100 (10 tasks, ablation)final accuracy A_N (%): 16.5 -> 33.7Improved
add real data distillation (ablation)Ours · CIFAR-100 (10 tasks, ablation)final accuracy A_N (%): 15.9 -> 33.7Improved
add synthetic data distillation (ablation)Ours · CIFAR-100 (10 tasks, ablation)final accuracy A_N (%): 12.7 -> 33.7Improved
add fine-tuning cross-entropy (FT-CE) loss (ablation)Ours · CIFAR-100 (10 tasks, ablation)final accuracy A_N (%): 9.8 -> 33.7Improved
use the proposed method instead of DeepInversion distillationOurs · CIFAR-100 (10 tasks, data-free)final accuracy A_N (%): 10.9 -> 33.7Improved
add synthetic data to LwFLwF · CIFAR-100 (10 tasks, data-free)final accuracy A_N (%): 9.2 -> 8.9No clear effect
add generative replay (DGR)Base · CIFAR-100 (10 tasks, data-free)final accuracy A_N (%): 8.8 -> 8.1Hurt
use the proposed data-free method instead of LwF with coreset replayOurs · CIFAR-100 (10 tasks, with replay coreset)final accuracy A_N (%): 27.4 -> 33.7Improved
store coreset replay and use BiC instead of the data-free methodBiC · CIFAR-100 (10 tasks, with replay coreset)final accuracy A_N (%): 33.7 -> 45.9Improved
proposed method vs LwF.MC at large resolutionOurs · ImageNet-50 (5 tasks)final accuracy A_N (%): 72.7 -> 71.5Hurt
use the proposed method instead of LwF without replayOurs · ImageNet-50 (5 tasks)final accuracy A_N (%): 19.4 -> 71.5Improved

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