AI Paper Atlas

Research map / Detection and segmentation / CNN features

Reverse Attention for Salient Object Detection

Shuhan Chen, Xiuli Tan, Ben Wang, Xuelong Hu

ECCV 2018 · Detection and segmentation › CNN features · approach: RGB salient object detection · 728 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 reverse attention to side-output residual learning (ablation)Ours · DUT-OMRONmax F-measure: 0.762 -> 0.786Improved
add reverse attention to side-output residual learning (ablation)Ours · DUT-OMRONMAE: 0.071 -> 0.062Improved
add reverse attention to side-output residual learning (ablation)Ours · PASCAL-Smax F-measure: 0.818 -> 0.834Improved
add reverse attention to side-output residual learning (ablation)Ours · PASCAL-SMAE: 0.106 -> 0.104Improved
add reverse attention to side-output residual learning (ablation)Ours · MSRA-Bmax F-measure: 0.919 -> 0.931Improved
add reverse attention to side-output residual learning (ablation)Ours · six saliency benchmarksmax F-measure and MAE: average 1.4% F-measure gain and 0.5% MAE decreaseImproved
set residual depth D=2 instead of D=1 (ablation)Ours · DUT-OMRONmax F-measure: 0.776 -> 0.786Improved
set residual depth D=2 instead of D=3 (ablation)Ours · DUT-OMRONmax F-measure: 0.778 -> 0.786Improved
set residual depth D=2 instead of D=1 (ablation)Ours · PASCAL-SMAE: 0.100 -> 0.104Hurt
combine more side-output residual features (side-output 5 to side-output 1) (ablation)Ours · PASCAL-Smax F-measure: 0.817 -> 0.834Improved
combine more side-output residual features (side-output 5 to side-output 1) (ablation)Ours · DUT-OMRONmax F-measure: 0.755 -> 0.786Improved
combine more side-output residual features (side-output 5 to side-output 1) (ablation)Ours · DUT-OMRONMAE: 0.071 -> 0.062Improved

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