atlas

Research map / Detection and segmentation / CNN features

Group Collaborative Learning for Co-Salient Object Detection

CVPR 2021 · Detection and segmentation › CNN features · approach: RGB salient object detection · 106 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
add GAM (ablation)GCoNet baseline · CoCASα: 0.591 -> 0.605Helped
add GCM (ablation)GCoNet baseline · CoCASα: 0.591 -> 0.616Helped
add ACM (ablation)GCoNet baseline · CoCASα: 0.591 -> 0.606Helped
combine GAM and GCM (ablation)GCoNet baseline · CoCASα: 0.591 -> 0.650Helped
add ACM to GAM and GCM (ablation)GCoNet · CoCASα: 0.650 -> 0.673Helped
use group-level affinity across the images instead of vanilla average-pooled consensus (ablation)GCoNet · CoCA, CoSOD3k, and Cosal2015Sα: 0.591 -> 0.605; 0.764 -> 0.772; 0.818 -> 0.825Helped
train with inter-group collaboration and zero-map supervision for cross-group features (ablation)GCoNet · CoCA, CoSOD3k, and Cosal2015Sα: 0.591 -> 0.616; 0.764 -> 0.788; 0.818 -> 0.834Helped
add auxiliary classification supervision (ablation)GCoNet · CoCA, CoSOD3k, and Cosal2015Sα: 0.591 -> 0.606; 0.764 -> 0.779; 0.818 -> 0.832Helped

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