atlas

Research map / Detection and segmentation / CNN features

Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing

CVPR 2019 · Detection and segmentation › CNN features · approach: RGB salient object detection · 103 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 multi-scale label-smoothing refinement (ablation)Mask-guided FCN · iCoseg, MSRC, and Cosal2015AP: iCoseg: 0.8395 -> 0.9057; MSRC: 0.8686 -> 0.9096; Cosal2015: 0.8372 -> 0.8527Helped
Add pool3 masking (ablation)Mask-guided FCN · iCoseg, MSRC, and Cosal2015AP: iCoseg: 0.8959 -> 0.9057; MSRC: 0.8875 -> 0.9096; Cosal2015: 0.8297 -> 0.8527Helped
Add pool5 masking (ablation)Mask-guided FCN · iCoseg, MSRC, and Cosal2015AP: iCoseg: 0.9007 -> 0.9057; MSRC: 0.8922 -> 0.9096; Cosal2015: 0.8335 -> 0.8527Helped

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