AI Paper Atlas

Research map / Continual learning / Class-incremental

Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer

Arjun Ashok, K J Joseph, Vineeth N Balasubramanian

ECCV 2022 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 41 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 CSCCT to iCaRLiCaRL · CIFAR100 (B=C=1)average incremental accuracy (%): 30.92 -> 34.02Improved
add CSCCT to LUCIRLUCIR · CIFAR100 (B=50, C=2)average incremental accuracy (%): 55.38 -> 56.49Improved
add CSCCT to PODNetPODNet · CIFAR100 (B=C=1)average incremental accuracy (%): 33.58 -> 36.23Improved
add CSCCT to PODNetPODNet · ImageNet-Subset (B=50, C=10)average incremental accuracy (%): 75.32 -> 76.41Improved
add CSCCT to LUCIRLUCIR · CIFAR100 (B=C=1)average incremental accuracy (%): 25.4 -> 28.12Improved
add Cross-Space Clustering alone (ablation)LUCIR · CIFAR100 (B=50, C=1)average incremental accuracy (%): 50.26 -> 52.04Improved
add Controlled Transfer alone (ablation)LUCIR · CIFAR100 (B=50, C=1)average incremental accuracy (%): 50.26 -> 51.5Improved
add Controlled Transfer alone (ablation)LUCIR · CIFAR100 (B=50, C=5)average incremental accuracy (%): 59.4 -> 61.97Improved
add Cross-Space Clustering alone (ablation)LUCIR · CIFAR100 (B=50, C=5)average incremental accuracy (%): 59.4 -> 60.45Improved
combine CSC and CT (full CSCCT) instead of CSC alone (ablation)LUCIR + CSC · CIFAR100 (B=C=1)average incremental accuracy (%): 27.16 -> 28.12Improved
increase batch size from 128 to 1024 (ablation)LUCIR · CIFAR100 (B=50, C=5)average incremental accuracy (%): 59.4 -> 54.83Hurt
increase batch size from 128 to 1024 (ablation)LUCIR + CSCCT · CIFAR100 (B=50, C=5)average incremental accuracy (%): 60.01 -> 57.8Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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