AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Learning, Fast and Slow

Quang Pham, Chenghao Liu, Steven C. H. Hoi

TPAMI 2023 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 138 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 fast learner on top of slow learner (ablation)DualNet · Split miniImageNet-TAACC: 68.33 -> 73.20Improved
add fast learner on top of slow learner (ablation)DualNet · Split miniImageNet-TFACC: 27.30 -> 36.86Improved
use Barlow Twins SSL objective instead of classification loss (ablation)DualNet · Split miniImageNet-TA (Look-ahead)ACC: 70.96 -> 73.20Improved
use Look-ahead optimizer instead of SGD for slow learner (ablation)DualNet (Barlow Twins) · Split miniImageNet-TAACC: 70.99 -> 73.20Improved
use Look-ahead optimizer instead of SGD for slow learner (ablation)DualNet++ (Barlow Twins) · Split miniImageNet-TAACC: 71.10 -> 74.24Improved
add spatial dropout (DualNet++) to DualNetDualNet · Split miniImageNet-TAACC: 73.20 -> 74.24Improved
add spatial dropout (DualNet++) to DualNetDualNet · Split miniImageNet-TA semi-supervised (rho=10%)ACC: 54.03 -> 58.03Improved
add spatial dropout (DualNet++) to DualNetDualNet · Split miniImageNet-TA semi-supervised (rho=25%)ACC: 62.80 -> 63.96Improved
add data augmentation to baselineER · Split miniImageNet-TAACC: 58.24 -> 59.80Improved
add DualNet slow-fast learners instead of baseline replayDER++-Aug · Split miniImageNet-TFACC: 28.26 -> 36.86Improved
add pre-trained ImageNet initializationDualNet · CTrL S- (task-free)ACC: 65.5 -> 66.7Improved
increase SSL iterations n from 1 to 20 between supervised updatesDualNet · Split miniImageNetACCImproved

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