atlas

Research map / Detection and segmentation / CNN features

Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection

CVPR 2022 · Detection and segmentation › CNN features · approach: RGB salient object detection · 81 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 DCFM instead of GCoNetCo-salient object detection · CoCAMAE: 0.105 -> 0.085Helped
Use DCFM instead of GCoNetCo-salient object detection · CoCAmaximum F-measure: 0.544 -> 0.598Helped
Use DCFM instead of GCoNetCo-salient object detection · CoSOD3kMAE: 0.071 -> 0.067Helped
Use DCFM instead of GCoNetCo-salient object detection · CoSOD3kmaximum F-measure: 0.777 -> 0.805Helped
Use DCFM instead of DeepACGCo-salient object detection · Cosal2015MAE: 0.064 -> 0.067Hurt
Use DCFM instead of DeepACGCo-salient object detection · Cosal2015maximum F-measure: 0.842 -> 0.856Helped
Add DPG to baseline (ablation)DCFM · CoCAMAE: 0.129 -> 0.097Helped
Add DPG to baseline (ablation)DCFM · CoCAmaximum F-measure: 0.521 -> 0.575Helped
Add SCL after DPG (ablation)DCFM · CoCAMAE: 0.097 -> 0.087Helped
Add DFE after DPG and SCL (ablation)DCFM · CoCAmaximum F-measure: 0.592 -> 0.598Helped
Add seed selection block after residual block (ablation)DPG · CoCAMAE: 0.124 -> 0.126Hurt
Add democratic response block (ablation)DPG with residual and seed selection blocks · CoCAMAE: 0.126 -> 0.097Helped

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