AI Paper Atlas

Research map / Continual learning / Class-incremental

CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning

Junghun Oh, Sungyong Baik, Kyoung Mu Lee

ECCV 2024 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 17 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 inter-class distance minimization (L_inter) on top of low temperature and SSC (ablation)CLOSER · CIFAR100whole-class accuracy A_W (%): 49.98 -> 53.32Improved
add L_inter on top of low temperature and SSC (ablation)CLOSER · CIFAR100base-class accuracy A_B (%): 66.58 -> 70.72Improved
add L_inter on top of low temperature and SSC (ablation)CLOSER · CIFAR100new-class accuracy A_N (%): 25.08 -> 27.23Improved
use lower temperature in softmax cross-entropy (ablation)baseline · CIFAR100new-class accuracy A_N (%): 20.95 -> 24.10Improved
use lower temperature in softmax cross-entropy (ablation)baseline · CIFAR100base-class accuracy A_B (%): 70.13 -> 68.33Hurt
add self-supervised contrastive loss L_ssc to baseline (ablation)baseline · CIFAR100new-class accuracy A_N (%): 20.95 -> 22.80Improved
add L_inter alone without any spreading loss (ablation)baseline · CIFAR100new-class accuracy A_N (%): 20.95 -> 20.05Hurt
apply CLOSER representation learning instead of baselineFSCIL with fixed feature extractor · CUB200performance drop PD (%): 19.83 -> 15.82Improved
CLOSER vs ALICE on miniImageNet last-session accuracyFSCIL · miniImageNetaccuracy (%): 55.70 -> 53.33Hurt

Later papers that compared with this method

2 later accepted papers report CLOSER as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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