AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Uncertain Convolutional Features for Accurate Saliency Detection

Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, Baocai Yin

ICCV 2017 · Detection and segmentation › CNN features · approach: RGB salient object detection · 493 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
replace plain dropout with R-Dropout (ablation)UCF (regular deconvolution) · ECSSDF-measure: 0.8166 -> 0.8356Improved
replace plain dropout with R-Dropout (ablation)UCF (regular deconvolution) · ECSSDMAE: 0.0811 -> 0.0781Improved
replace plain dropout with R-Dropout (ablation)UCF (regular deconvolution) · DUT-OMRONF-measure: 0.6128 -> 0.6168Improved
replace plain dropout with R-Dropout (ablation)UCF (regular deconvolution) · PASCAL-SF-measure: 0.6172 -> 0.6845Improved
replace regular deconvolution with interpolation upsampling (ablation)UCF with R-Dropout · ECSSDF-measure: 0.8356 -> 0.8426Improved
replace regular deconvolution with interpolation upsampling (ablation)UCF with R-Dropout · PASCAL-SF-measure: 0.6845 -> 0.7201Improved
use hybrid upsampling instead of interpolation only (ablation)UCF with R-Dropout · ECSSDF-measure: 0.8426 -> 0.8517Improved
use hybrid upsampling instead of deconvolution only (ablation)UCF with R-Dropout · ECSSDF-measure: 0.8356 -> 0.8517Improved
use hybrid upsampling instead of interpolation only (ablation)UCF with R-Dropout · SED1F-measure: 0.8665 -> 0.8647No clear effect
add R-Dropout to interpolation-only upsampling model (ablation)UCF without dropout · ECSSDF-measure: 0.7857 -> 0.8426Improved
add R-Dropout to deconvolution-only upsampling model (ablation)UCF without dropout · ECSSDF-measure: 0.6942 -> 0.8356Improved
use hybrid upsampling instead of regular deconvolution (ablation)UCF · PASCAL VOC 2012 segmentationmean IoU: 65.173 -> 67.45Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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