Research map / Detection and segmentation / CNN features
DeepACG: Co-Saliency Detection via Semantic-Aware Contrast Gromov-Wasserstein Distance
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 |
|---|---|---|---|
| add GW matching (ablation) | DeepACG · CoCA | Fβ: 0.529 -> 0.552 | Helped |
| add SCAM (ablation) | DeepACG · CoCA | Fβ: 0.529 -> 0.552 | Helped |
| add GW matching and SCAM together (ablation) | DeepACG · CoCA | Fβ: 0.443 -> 0.552 | Helped |
| add EEM (ablation) | DeepACG · CoCA | Fβ: 0.532 -> 0.552 | Helped |
| replace GW matching with NLA (ablation) | DeepACG · CoCA | Fβ: 0.552 -> 0.532 | Hurt |
| replace GW matching with EMD (ablation) | DeepACG · CoCA | Fβ: 0.552 -> 0.535 | Hurt |
| use DeepACG rather than GICD | Co-saliency detection · Cosal2015 | Fβ: 0.834 -> 0.842 | Helped |
| use DeepACG rather than GICD | Co-saliency detection · CoSOD3k | Fβ: 0.743 -> 0.756 | Helped |
| use DeepACG rather than GCAGC | Co-saliency detection · CoCA | Fβ: 0.523 -> 0.552 | Helped |
Closest papers by meaning
- Robust Deep Co-Saliency Detection with Group Semantic (AAAI 2019 · similarity 0.90)
- ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020 · similarity 0.89)
- Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection (CVPR 2020 · similarity 0.89)
- Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing (CVPR 2019 · similarity 0.88)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · 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.