AI Paper Atlas

Research map / Continual learning / Online and replay-based

Adversarial Continual Learning

Sayna Ebrahimi, Franziska Meier, Roberto Calandra, Trevor Darrell, Marcus Rohrbach

ECCV 2020 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 189 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 adversarial discriminator D to shared and private modules (ablation)ACL (S+P) · 20-Split miniImageNetACC: 50.15 -> 55.72Improved
add adversarial discriminator D to shared and private modules (ablation)ACL (S+P) · 20-Split miniImageNetBWT: -14.32 -> -0.12Improved
add orthogonality difference loss to shared and private modules (ablation)ACL (S+P) · 20-Split miniImageNetACC: 50.15 -> 49.13No clear effect
add orthogonality difference loss to shared and private modules (ablation)ACL (S+P) · 20-Split miniImageNetBWT: -14.32 -> -3.99Improved
add difference loss to S+P+D (ablation)ACL · 20-Split miniImageNetACC: 55.72 -> 57.66Improved
add one-sample-per-class replay buffer to S+P+D+Ldiff (ablation)ACL · 20-Split miniImageNetACC: 57.66 -> 62.07Improved
add one-sample-per-class replay buffer to S+P+D+Ldiff (ablation)ACL · 20-Split miniImageNetBWT: -3.71 -> 0.00Improved
add discriminator rather than difference loss given replay buffer (ablation)ACL + RB · 20-Split miniImageNetACC: 52.07 -> 60.28Improved
add shared module to private modules, discriminator and more components (shared only vs private only) (ablation)ACL · 20-Split miniImageNetACC: 29.09 -> 21.19Hurt
add replay buffer to S+P (ablation)ACL (S+P) · 20-Split miniImageNetACC: 50.15 -> 51.19Improved
increase replay samples per class from 1 to 13ER-RES · 20-Split miniImageNetACC: 40.21 -> 57.32Improved
increase replay samples per class from 1 to 13ACL · 20-Split miniImageNetACC: 62.07 -> 61.33No clear effect

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