AI Paper Atlas

Research map / Detection and segmentation / CNN features

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu

ICCV 2019 · Detection and segmentation › CNN features · approach: RGB salient object detection · 527 citations (OpenAlex)

This paper tried a common change: Add attention module

add the recurrent attention module RAM on top of DMSW · RGB-D saliency, proposed dataset · F-measure: 0.861 -> 0.883 Improved

What 492 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 the DRB multi-level fusion module over the common fusion baseline (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.828 -> 0.839Improved
add the DRB multi-level fusion module over the common fusion baseline (ablation)DMRANet · RGB-D saliency, proposed datasetMAE: 0.070 -> 0.065Improved
add the DMSW module (depth-induced multi-scale weighting) on top of DRB (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.839 -> 0.861Improved
add depth guidance to multi-scale feature integration in DMSW (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.855 -> 0.861Improved
add depth guidance to multi-scale feature integration in DMSW (ablation)DMRANet · RGB-D saliency, NLPRF-measure: 0.805 -> 0.801Hurt
add the recurrent attention module RAM on top of DMSW (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.861 -> 0.883Improved
use RAM instead of common channel-spatial attention (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.869 -> 0.883Improved
use RAM instead of common channel-spatial attention (ablation)DMRANet · RGB-D saliency, proposed datasetMAE: 0.054 -> 0.048Improved
add common channel-spatial attention on top of DMSW (ablation)DMRANet · RGB-D saliency, proposed datasetF-measure: 0.861 -> 0.869Improved
use DMRANet instead of the best prior RGB-D CNN (PAGRN)RGB-D saliency · RGB-D saliency, proposed datasetF-measure: 0.836 -> 0.883Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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