AI Paper Atlas

Research map / Detection and segmentation / CNN features

Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition

Ming Sun, Yuchen Yuan, Feng Zhou, Errui Ding

ECCV 2018 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 443 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 OSME module without MAMC (ablation)ResNet-50 · CUB-200-2011top-1 accuracy (%): 81.7 -> 84.9Improved
use OSME instead of two independent FC layers under MAMC (ablation)ResNet-50 + MAMC · CUB-200-2011top-1 accuracy (%): 85.7 -> 86.2Improved
add first MAMC constraint on top of OSME (ablation)ResNet-50 + OSME · CUB-200-2011top-1 accuracy (%): 84.9 -> 85.4Improved
add the remaining two MAMC constraints (ablation)ResNet-50 + OSME + MAMC · CUB-200-2011top-1 accuracy (%): 85.4 -> 86.2Improved
increase attention regions from P=2 to P=3 (ablation)ResNet-50 + OSME + MAMC · CUB-200-2011top-1 accuracy (%): 86.2 -> 86.3No clear effect
use ResNet-101 instead of ResNet-50 backbone (ablation)OSME + MAMC · CUB-200-2011top-1 accuracy (%): 86.2 -> 86.5Improved
full method versus ResNet-50 baselineResNet-50 · CUB-200-2011top-1 accuracy (%): 81.7 -> 86.2Improved
full method versus RACNN, multi-stageRACNN · Dogs-in-the-Wildtop-1 accuracy (%): 76.5 -> 77.9Improved
full method versus RACNN on Stanford DogsRACNN · Stanford Dogstop-1 accuracy (%): 87.3 -> 85.2Hurt
ResNet-101 OSME+MAMC vs ResNet-101 baseline on Stanford CarsResNet-101 · Stanford Carstop-1 accuracy (%): 91.9 -> 93.0Improved

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