AI Paper Atlas

Research map / Continual learning / Online and replay-based

CoSCL: Cooperation of Small Continual Learners Is Stronger than a Big One

Liyuan Wang, Xingxing Zhang, Qian Li, Jun Zhu, Yi Zhong

ECCV 2022 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 43 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 CoSCL (5 small learners)EWC · CIFAR-100-SC (A20)averaged accuracy: 51.74 -> 60.84Improved
add CoSCL (5 small learners)EWC · CIFAR-100-RS (A20)averaged accuracy: 69.18 -> 76.05Improved
add CoSCL (5 small learners)MAS · CIFAR-100-SC (A20)averaged accuracy: 52.18 -> 60.69Improved
add CoSCL (5 small learners)EWC · CUB-200-2011 (A10)averaged accuracy: 42.29 -> 48.53Improved
add CoSCL (5 small learners)EWC · Tiny-ImageNet (A10)averaged accuracy: 48.38 -> 55.10Improved
use feature ensemble of small learners instead of single learner (ablation)EWC · CIFAR-100-SC (A20)averaged accuracy: 51.74 -> 57.69Improved
use classifier ensemble instead of single learnerEWC · CIFAR-100-SC (A20)averaged accuracy: 51.74 -> 43.88Hurt
add ensemble cooperation loss to feature ensemble (ablation)Feature Ensemble · CIFAR-100-SC (A20)averaged accuracy: 57.69 -> 59.49Improved
add task-adaptive gates to feature ensemble (ablation)Feature Ensemble · CIFAR-100-SC (A20)averaged accuracy: 57.69 -> 59.85Improved
add task-adaptive gates to feature ensemble with EC (ablation)Feature Ensemble + EC · CIFAR-100-SC (A20)averaged accuracy: 59.49 -> 60.84Improved
add ensemble cooperation loss to feature ensemble with gates (ablation)Feature Ensemble + TG · CIFAR-100-SC (A20)averaged accuracy: 59.85 -> 60.84Improved
add CoSCL to unsupervised continual learningSimSiam · CIFAR-100-RS unsupervised CLaveraged accuracy: 41.38 -> 46.33Improved

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