Research map / Graph learning / Graph algorithms and clustering
Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use GCAGC instead of CSMG | co-saliency detection · iCoseg | F_beta: 0.8517 -> 0.8532 | Helped |
| Use GCAGC instead of CSMG | co-saliency detection · Cosal2015 | F_beta: 0.8216 -> 0.8428 | Helped |
| Use GCAGC instead of RCGS | co-saliency detection · COCO-SEG | F_beta: 0.6814 -> 0.7092 | Helped |
| Add AGCN (ablation) | GCAGC · Cosal2015 | AP: 0.8577 -> 0.8799 | Helped |
| Add AGCN (ablation) | GCAGC · Cosal2015 | F_beta: 0.8156 -> 0.8428 | Helped |
| Add AGCN (ablation) | GCAGC · iCoseg | F_beta: 0.8504 -> 0.8532 | Helped |
| Add AGCM (ablation) | GCAGC · iCoseg | AP: 0.8606 -> 0.8867 | Helped |
| Add AGCM (ablation) | GCAGC · iCoseg | F_beta: 0.8123 -> 0.8532 | Helped |
| Add AGCM (ablation) | GCAGC · Cosal2015 | F_beta: 0.8373 -> 0.8428 | Helped |
| Use learnable projection matrices P for adaptive graph learning (ablation) | AGCN in GCAGC · iCoseg | AP: 0.8796 -> 0.8867 | Helped |
| Use learnable projection matrices P for adaptive graph learning (ablation) | AGCN in GCAGC · Cosal2015 | F_beta: 0.8375 -> 0.8428 | Helped |
| Add AGCM (ablation) | GCAGC · Cosal2015 | MAE: 0.0901 -> 0.0890 | Mixed |
Closest papers by meaning
- Multi-scale Graph Fusion for Co-saliency Detection (AAAI 2021 · similarity 0.92)
- 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 0.89)
- DeepACG: Co-Saliency Detection via Semantic-Aware Contrast Gromov-Wasserstein Distance (CVPR 2021 · similarity 0.89)
- Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing (CVPR 2019 · similarity 0.88)
- Recurrent Attentional Networks for Saliency Detection (CVPR 2016 · similarity 0.88)
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.