AI Paper Atlas

Research map / Continual learning / Class-incremental

Topology-Preserving Class-Incremental Learning

Xiaoyu Tao, Xinyuan Chang, Xiaopeng Hong, Xing Wei, Yihong Gong

ECCV 2020 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 171 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
use TPCIL instead of LUCIRclass-incremental CNN · CIFAR100 (5 sessions)average accuracy (%): 63.42 -> 65.34Improved
use TPCIL instead of LUCIRclass-incremental CNN · subImageNet (10 sessions)average accuracy (%): 68.09 -> 74.81Improved
use TPCIL instead of LUCIRclass-incremental CNN · ImageNet (5 sessions)average accuracy (%): 64.34 -> 64.89Improved
use TPL instead of feature distillation loss (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 60.55 -> 65.34Improved
use TPL instead of logit distillation loss (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 55.61 -> 65.34Improved
use correlation-form TPL instead of l1 form (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 64.17 -> 65.34Improved
use correlation-form TPL instead of l2 form (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 62.75 -> 65.34Improved
add logit distillation loss to TPL (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 65.34 -> 56.19Hurt
add feature distillation loss to TPL (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 65.34 -> 58.66Hurt
use EHG vertices instead of random exemplars (1 per class) (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 33.86 -> 42.26Improved
use EHG vertices instead of random exemplars (20 per class) (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 64.70 -> 65.34Improved
add TPL term (lambda 0 -> 15) (ablation)TPCIL · CIFAR100 (5 sessions)average accuracy (%): 22.34 -> 65.34Improved

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