atlas

Research map / Detection and segmentation / CNN features

Saliency Unified: A Deep Architecture for Simultaneous Eye Fixation Prediction and Salient Object Segmentation

CVPR 2016 · Detection and segmentation › CNN features · approach: RGB salient object detection · 151 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use the unified CNN with CRF refinement for salient-object segmentationSaliency Unified · DUT-OMRONMAE: 0.09 -> 0.07Helped
Add CRF refinement to the segmentation CNN (ablation)Saliency Unified · DUT-OMRONmean Fwβ: 0.65 -> 0.68Helped
Train shared layers simultaneously for fixation and segmentation instead of independently (ablation)Saliency Unified · DUT-OMRONNSS: 2.80 -> 3.02Helped
Train shared layers simultaneously for fixation and segmentation instead of independently (ablation)Saliency Unified · DUT-OMRONEMD: 1.07 -> 1.03Helped
Train shared layers simultaneously for fixation and segmentation instead of independently (ablation)Saliency Unified · DUT-OMRONMAE: 0.07 -> 0.07No clear effect
Train shared layers simultaneously for fixation and segmentation instead of independently (ablation)Saliency Unified · DUT-OMRONFwβ: 0.67 -> 0.68Helped
Use the unified CNN for eye-fixation predictionSaliency Unified · DUT-OMRONNSS: 2.03 -> 3.02Helped

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