AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Deep Relations to Promote Saliency Detection

Changrui Chen, Xin Sun, Yang Hua, Junyu Dong, Hongwei Xv

AAAI 2020 · Detection and segmentation › CNN features · approach: RGB salient object detection · 21 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
refine PFA with MI relation modelPFA · ECSSDF-measure: 0.8863 -> 0.9138Improved
refine weak conventional detector wCtrOwCtrO · ECSSDF-measure: 0.6763 -> 0.8537Improved
refine strongest detector R3NetR3Net · ECSSDF-measure: 0.9148 -> 0.9208Improved
refine PFA with MI relation modelPFA · ECSSDMAE: 0.0448 -> 0.0383Improved
refine PiCANetPiCANet · DUT-OMRONF-measure: 0.7496 -> 0.7899Improved
use our method instead of LPS for refinementAmulet · ECSSDF-measure: 0.8963 -> 0.9069Improved
use our method instead of DenseCRFsUCF · ECSSDF-measure: 0.847 -> 0.878Improved
lower foreground threshold theta_fg from 0.9 to 0.7 at test (ablation)SRM + ours · ECSSDF-measure: 0.9158 -> 0.9152No clear effect
vary approximate thresholds theta_afg/theta_abg in training (ablation)SRM + ours · ECSSDF-measure: 0.9154 vs 0.9145 and 0.9149No clear effect

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