AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering

Chuang Niu, Jun Zhang, Ge Wang, Jimin Liang

ECCV 2020 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 85 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 attention mapping module (ablation)GATCluster · STL10best ACC: 0.539 -> 0.583Improved
add attention mapping module (ablation)GATCluster · STL10mean ACC: 0.494 -> 0.537Improved
use grayscale instead of color images (ablation)GATCluster · STL10best ACC: 0.556 -> 0.583Improved
add transformation invariance task (ablation)GATCluster · STL10best ACC: 0.576 -> 0.583Improved
add separability maximization task (ablation)GATCluster · STL10best ACC: 0.579 -> 0.583Improved
add separability maximization task (ablation)GATCluster · STL10mean ACC: 0.529 -> 0.537Improved
add transformation invariance task (ablation)GATCluster · STL10mean ACC: 0.546 -> 0.537No clear effect
add entropy analysis task (ablation)GATCluster · STL10clusteringImproved
increase input size from 96x96 to 128x128 (ablation)GATCluster · ImageNet-10best ACC: 0.739 -> 0.762Improved
increase input size from 128x128 to 160x160 (ablation)GATCluster · ImageNet-10best ACC: 0.762 -> 0.712Hurt
increase input size from 128x128 to 192x192 (ablation)GATCluster · ImageNet-10mean ACC: 0.735 -> 0.608Hurt
use 6x6 attention map instead of 2x2 (ablation)GATCluster · ImageNet-10best ACC: 0.746 -> 0.762Improved

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