AI Paper Atlas

Research map / Detection and segmentation / CNN features

Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs

Youbao Tang, Xiangqian Wu

ECCV 2016 · Detection and segmentation › CNN features · approach: RGB salient object detection · 80 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
add joint training of pixel-level CNN and fusion CNN (ablation)sep-CRPSD · SEDweighted F-measure: 0.8109 -> 0.8292Improved
add joint training of pixel-level CNN and fusion CNN (ablation)sep-CRPSD · ECSSDweighted F-measure: 0.8249 -> 0.8485Improved
add joint training of pixel-level CNN and fusion CNN (ablation)sep-CRPSD · PASCAL-Sweighted F-measure: 0.7621 -> 0.7761Improved
add joint training of pixel-level CNN and fusion CNN (ablation)sep-CRPSD · HKU-ISweighted F-measure: 0.7942 -> 0.8209Improved
fuse region-level saliency and original image with pixel-level map via fusion CNN (ablation)PSD · SEDweighted F-measure: 0.7590 -> 0.8292Improved
fuse region-level saliency and original image with pixel-level map via fusion CNN (ablation)PSD · ECSSDweighted F-measure: 0.7572 -> 0.8485Improved
fuse region-level saliency and original image with pixel-level map via fusion CNN (ablation)PSD · PASCAL-Sweighted F-measure: 0.7113 -> 0.7761Improved
fuse region-level saliency and original image with pixel-level map via fusion CNN (ablation)PSD · HKU-ISweighted F-measure: 0.7371 -> 0.8209Improved
fuse pixel-level saliency and original image with region-level map via fusion CNN (ablation)RSD · PASCAL-Sweighted F-measure: 0.6195 -> 0.7761Improved
train for saliency instead of using semantic segmentation model directlypre-DML · ECSSDweighted F-measure: 0.6530 -> 0.7482Improved
train for saliency instead of using semantic segmentation model directlypre-DML · PASCAL-Sweighted F-measure: 0.7322 -> 0.6948Hurt
adaptive regions and region-centered context windows instead of superpixels (RSD vs MC)MC · PASCAL-Sweighted F-measure: 0.6064 -> 0.6195Improved

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