AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Top-Down Neural Attention by Excitation Backprop

Jianming Zhang, Zhe Lin, Jonathan Brandt, Xiaohui Shen, Stan Sclaroff

ECCV 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 820 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 contrastive attention (c-MWP vs MWP)Excitation Backprop · VOC07 Test (difficult subset), GoogleNetPointing Game accuracy (%): 60.4 -> 72.3Improved
add contrastive attention (c-MWP vs MWP)Excitation Backprop · COCO Val (difficult subset), GoogleNetPointing Game accuracy (%): 37.1 -> 48.3Improved
add the probabilistic normalization factor Z_i (ablation)contrastive Excitation Backprop · Pointing GameMean accuracy (%): 41.6 -> 70.6Improved
propagate contrastive signal in a single pass instead of subtracting after L1 normalization (ablation)contrastive Excitation Backprop · Pointing GameMean accuracy (%): 58.1 -> 70.6Improved
apply contrastive attention to DeconvDeconv · Pointing GameMean accuracy (%): 49.4 -> 67.7Improved
apply contrastive attention to CAMCAM · Pointing GameMean accuracy (%): 61.9 -> 61.9No clear effect
apply contrastive attention to GradGrad · Pointing GameMean accuracy (%)Hurt
use contrastive attention (c-MWP vs MWP)Excitation Backprop · ImageNet Val dominant object localizationLocalization error (%): 38.7 -> 57.0Hurt
use attention at I5b/out layer instead of intermediate layers (ablation)c-MWP vs Grad/Deconv · Pointing Game, GoogleNet layer selectionPointing Game accuracyMixed
add contrastive attention (c-MWP vs MWP)Excitation Backprop · Flickr30k Entities, MCGRecall@1 (%): 28.5 -> 26.2Hurt
add contrastive attention (c-MWP vs MWP)Excitation Backprop · Flickr30k Entities, MCGmAP (Group): 11.8 -> 15.2Improved
re-score MCG proposals with MWP attentionMCG_base · Flickr30k EntitiesRecall@1 (%): 10.7 -> 28.5Improved

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