AI Paper Atlas

Research map / Continual learning / Online and replay-based

Bi-Objective Continual Learning: Learning ‘New’ While Consolidating ‘Known’

Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Yihong Gong

AAAI 2020 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 29 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 pillar consolidation (PLC) loss with SOM pillars (ablation)finetuning on new instances · CIFAR10 ST-NILaccuracy (%): up to 9.22% over naiveImproved
add contrastive pillar (CPL) loss to PLC (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 76.98 -> 77.43Improved
use SOM pillars instead of random exemplars for CPL+PLC (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 76.62 -> 77.43Improved
add feature re-weighting omega to PLC with SOM pillars (ablation)PLC · CIFAR10 ST-NILaccuracy (%): 75.93 -> 76.98Improved
add feature re-weighting omega with random selection (ablation)PLC · CIFAR10 ST-NILaccuracy (%): 75.72 -> 75.72No clear effect
BOCL vs A-GEM* baseline on CIFAR100 full datacontinual learning · CIFAR100 ST-NILaccuracy (%): 51.24% -> 53.76%Improved
BOCL vs IMM* on subImageNet full datacontinual learning · subImageNettop-5 accuracy (%): 48.52% -> 50.32%Improved
finetune on hard or misclassified examples instead of random samples (ablation)finetuning · CIFAR10 ST-NILaccuracy (%)Hurt
increase lambda from 0.1 to 10 (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 69.77 -> 72.10Improved
increase lambda from 10 to 50 (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 72.10 -> 72.06No clear effect
increase gamma from 0.1 to 10 (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 71.31 -> 72.10Improved
increase pillars from 10 to 225 (ablation)BOCL · CIFAR10 ST-NILaccuracy (%): 69.43 -> 72.10Improved

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