Research map / Detection and segmentation / CNN features
ICNet: Intra-saliency Correlation Network 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 |
|---|---|---|---|
| add correlation fusion module (CFM) instead of concatenating group-level vector (ablation) | ICNet (NFs) · Cosal2015 | max F-measure: 0.788 -> 0.815 | Helped |
| add SISMs to build SIVs (ablation) | ICNet with NFs and CFM · Cosal2015 | max F-measure: 0.815 -> 0.824 | Helped |
| add SISMs to build SIVs (ablation) | ICNet with NFs and CFM · iCoseg | max F-measure: 0.726 -> 0.864 | Helped |
| replace l2-normalized features with self-correlation features (SCFs) (ablation) | ICNet with CFM and SISMs · Cosal2015 | max F-measure: 0.824 -> 0.855 | Helped |
| replace l2-normalized features with SCFs (no CFM, no SISMs) (ablation) | ICNet · Cosal2015 | max F-measure: 0.788 -> 0.767 | Hurt |
| replace l2-normalized features with SCFs (ablation) | ICNet with CFM and SISMs · iCoseg | max F-measure: 0.864 -> 0.857 | Hurt |
| add rearranging of SCF channels (RSCF) (ablation) | ICNet with SCFs · Cosal2015 | max F-measure: 0.855 -> 0.860 | Helped |
| add rearranging of SCF channels (RSCF) (ablation) | ICNet with SCFs · MSRC | max F-measure: 0.872 -> 0.869 | Mixed |
| apply ICNet on top of single-image SOD maps from GC | GC baseline · Cosal2015 | max F-measure: 0.640 -> 0.682 | Helped |
| apply ICNet on top of EGNet SISMs | EGNet baseline · Cosal2015 | max F-measure: 0.753 -> 0.860 | Helped |
Closest papers by meaning
- Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing (CVPR 2019 · similarity 0.89)
- Robust Deep Co-Saliency Detection with Group Semantic (AAAI 2019 · similarity 0.89)
- DeepACG: Co-Saliency Detection via Semantic-Aware Contrast Gromov-Wasserstein Distance (CVPR 2021 · similarity 0.89)
- Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection (CVPR 2020 · similarity 0.89)
- Multi-scale Graph Fusion for Co-saliency Detection (AAAI 2021 · similarity 0.88)
- Unsupervised Salient Instance Detection (CVPR 2024 · similarity 0.86)
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.