AI Paper Atlas

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

Deep Imbalanced Attribute Classification using Visual Attention Aggregation

Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 236 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 class weights to ResNet-101 baseline (ablation)ResNet-101 · WIDER-AttributemAP: 83.7 -> 84.0Improved
add instance-level focal weighting on top of class weights (Lw) (ablation)ResNet-101 · WIDER-AttributemAP: 84.0 -> 84.4Improved
add visual attention at a single scale (ablation)ResNet-101 + Lw · WIDER-AttributemAP: 84.4 -> 85.0Improved
add attention loss La (ablation)ResNet-101 + Lw + attention · WIDER-AttributemAP: 85.0 -> 85.7Improved
add multi-scale attention (without La) (ablation)ResNet-101 + Lw + attention · WIDER-AttributemAP: 85.0 -> 85.9Improved
add multi-scale attention on top of La (ablation)ResNet-101 + Lw + attention + La · WIDER-AttributemAP: 85.7 -> 86.4Improved
swap primary network from ResNet-50 to DenseNet-201 (ablation)primary net only · WIDER-AttributemAP: 82.3 -> 84.5Improved
add weighted focal loss Lw in place of LbSRN* · PETAF1: 83.25 -> 84.92Improved
add Lw to DenseNet-121 with class weights (ablation)DenseNet-121 · PETAF1: 82.1 -> 82.9Improved
add attention (ablation)DenseNet-121 + Lw · PETAF1: 82.9 -> 83.8Improved
add multi-scale with feature-level aggregation (ablation)DenseNet-121 + attention · PETAF1: 83.8 -> 84.1Improved
use score-level instead of feature-level multi-scale aggregation (ablation)DenseNet-121 + attention · PETAF1: 84.1 -> 84.7Improved

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