Research map / Detection and segmentation / CNN features
Multi-scale Graph Fusion for Co-saliency Detection
Read the paperCheck 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 changed | Where | Measured | Effect |
|---|---|---|---|
| use multi-scale features with graph fusion instead of MGLCN | co-saliency detection · iCoseg, Cosal2015, MSRC (average) | AUC: 1.13% | Helped |
| use multi-scale features with graph fusion instead of MGLCN | co-saliency detection · iCoseg, Cosal2015, MSRC (average) | Fβ: 0.12% | Mixed |
| use multi-scale features with graph fusion instead of MGLCN | co-saliency detection · iCoseg, Cosal2015, MSRC (average) | Sα: 4.82% | Helped |
| use multi-scale features with graph fusion instead of MGLCN | co-saliency detection · iCoseg, Cosal2015, MSRC (average) | AP: 5.03% | Helped |
| add cross-scale feature fusion to combine common and complementary information (ablation) | proposed co-saliency framework · iCoseg, Cosal2015, MSRC | AUC: 9.4% | Helped |
| add cross-scale feature fusion to combine common and complementary information (ablation) | proposed co-saliency framework · iCoseg, Cosal2015, MSRC | Fβ: 11.32% | Helped |
| add cross-scale feature fusion to combine common and complementary information (ablation) | proposed co-saliency framework · iCoseg, Cosal2015, MSRC | Sα: 8.93% | Helped |
| add cross-scale feature fusion to combine common and complementary information (ablation) | proposed co-saliency framework · iCoseg, Cosal2015, MSRC | AP: 9.29% | Helped |
| treat co-saliency detection as regression rather than binary classification (ablation) | proposed framework · three example images across the used datasets | boundary clarity | Mixed |
Closest papers by meaning
- Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection (CVPR 2020 · similarity 0.92)
- Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing (CVPR 2019 · similarity 0.90)
- Robust Deep Co-Saliency Detection with Group Semantic (AAAI 2019 · similarity 0.89)
- ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020 · similarity 0.88)
- GraB: Visual Saliency via Novel Graph Model and Background Priors (CVPR 2016 · similarity 0.88)
- DeepACG: Co-Saliency Detection via Semantic-Aware Contrast Gromov-Wasserstein Distance (CVPR 2021 · similarity 0.87)
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.