atlas

Research map / Detection and segmentation / CNN features

DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection

CVPR 2019 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 82 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 co-saliency information to the proposal ranking function (ablation)DeepCO3 · COCO-VOCmAPr 0.25: 33.5 -> 52.6Helped
Add co-saliency information to the proposal ranking function (ablation)DeepCO3 · COCO-VOCmAPr 0.5: 12.4 -> 21.1Helped
Add co-saliency information to the proposal ranking function (ablation)DeepCO3 · COCO-NONVOCmAPr 0.25: 25.3 -> 35.3Helped
Add co-saliency information to the proposal ranking function (ablation)DeepCO3 · COCO-NONVOCmAPr 0.5: 8.3 -> 12.3Helped
Add co-peak loss to the objective (ablation)DeepCO3 · COCO-VOC and COCO-NONVOCmAPr 0.25Helped
Add affinity loss to the objective (ablation)DeepCO3 · COCO-VOC and COCO-NONVOCmAPr 0.25Helped

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