atlas

Research map / Detection and segmentation / CNN features

A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond

CVPR 2016 · Detection and segmentation › CNN features · approach: RGB salient object detection · 64 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 FUCOS for gaze prediction instead of existing saliency algorithmsGaze prediction · Bruce, Judd, PASCAL, and ImgSalshuffled AUCHelped
Replace SALICON with FUCOSGaze prediction · Bruce, Judd, PASCAL, and ImgSalshuffled AUCMixed
Train SAL-FCN for salient-object segmentationSalient-object segmentation · PASCALF-ScoreHelped
Use SAL-DC instead of SAL-FCNSalient-object segmentation · PASCALprecisionHelped
Normalize ground-truth fixation maps to compensate for center bias (ablation)FUCOS gaze prediction · PASCALAUCHelped
Vary the percentile threshold used to binarize fixation-density maps (ablation)FUCOS gaze prediction · PASCALAUCMixed
Train on a varied combination of gaze datasets rather than data from a single datasetFUCOS · Gaze prediction across four datasetsshuffled AUCHelped

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