AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Neuromanifold-Regularized KANs for Shape-fair Feature Representations

Mazlum Ferhat Arslan, Weihong Guo, Shuo Li

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 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 hybrid basis (different degrees in early and later layers) (ablation)VGG-Gram CKAN · Tiny ImageNet cue-conflictshape bias: +5.1%Improved
add hybrid basis (ablation)VGG-Gram CKAN · Tiny ImageNet valtop-1 accuracy: -3.8%Hurt
add fused features from two branches (ablation)VGG-Gram CKAN + hybrid basis · Tiny ImageNet cue-conflictshape bias: +6.0%Improved
add fused features from two branches (ablation)VGG-Gram CKAN + hybrid basis · Tiny ImageNet valtop-1 accuracy: -4.4%Hurt
add style decorrelation loss (ablation)NMR-KAN · Tiny ImageNet cue-conflictshape bias: +3.7%Improved
add style decorrelation loss (ablation)NMR-KAN · Tiny ImageNet valtop-1 accuracy: +0.9%Improved
add hybrid basis (ablation)VGG-Gram CKAN · Tiny ImageNet-Crelative mCE: 105.7 -> 100.1Improved
add fused features (ablation)VGG-Gram + hybrid basis · Tiny ImageNet-Crelative mCE: 100.1 -> 95.1Improved
add style decorrelation loss (ablation)NMR-KAN · Tiny ImageNet-Crelative mCE: 95.1 -> 92.5Improved
vary uniform activation degree across all layers (2 to 7) (ablation)VGG-Gram CKAN · Tiny ImageNet cue-conflictshape bias: 41.5 -> 42.0No clear effect
use heterogeneous degrees (7,3) in a single extractor (ablation)VGG-Gram CKAN · Tiny ImageNet cue-conflictshape bias: 42.9% vs baseline 42.5Improved
use heterogeneous degrees (2,3) or (3,2) (ablation)VGG-Gram CKAN · Tiny ImageNet cue-conflictshape bias: 47.65% shape biasImproved

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