AI Paper Atlas

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

Contrastive Attention Maps for Self-Supervised Co-Localization

Minsong Ki, Youngjung Uh, Junsuk Choe, Hyeran Byun

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 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 classification loss Lcls to CAML+PTAP (ablation)Ours · CUB-200-2011, VGG16, rotationCorLoc Mean: 70.74 -> 73.20Improved
add contrastive attention map loss Lcaml (ablation)Baseline + PTAP · CUB-200-2011, VGG16, rotationCorLoc Mean: 69.44 -> 73.20Improved
add pixel-wise top-k attention pooling (ablation)CAML model · CUB-200-2011, VGG16, rotationCorLoc Mean: 69.50 -> 73.20Improved
compute contrastive loss on attention maps instead of feature maps (ablation)Lcaml · CUB-200-2011, VGG16, rotationCorLoc Mean: 67.92 -> 73.20Improved
add negative pairs (ablation)Lcaml · CUB-200-2011, VGG16, rotationCorLoc Mean: 70.16 -> 73.20Improved
add positive pairs (ablation)Lcaml · CUB-200-2011, VGG16, rotationCorLoc Mean: 67.92 -> 73.20Improved
use top-70% pooling instead of max pooling (ablation)PTAP · CUB-200-2011, VGG16, rotationCorLoc Mean: 58.01 -> 73.20Improved
use top-70% pooling instead of average pooling (ablation)PTAP · CUB-200-2011, VGG16, rotationCorLoc Mean: 70.94 -> 73.20Improved
use top-70% pooling instead of bottom-30% pooling (ablation)PTAP · CUB-200-2011, VGG16, rotationCorLoc Mean: 54.89 -> 73.20Improved
add CAML+PTAP to rotation pretext baseline (ablation)classification-only baseline · CUB-200-2011, VGG16, rotationCorLoc IoU=0.5: 77.21 -> 83.65 (+6.4)Improved
add CAML+PTAP to scale pretext baseline (ablation)classification-only baseline · CUB-200-2011, VGG16, scaleCorLoc IoU=0.5: 44.66 -> 83.62 (+39.0)Improved
add CAML+PTAP to translation pretext baseline (ablation)classification-only baseline · CUB-200-2011, VGG16, translationCorLoc IoU=0.5: 22.98 -> 83.05 (+60.1)Improved

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