Research map / Detection and segmentation / CNN features
CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object 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 OIaSG saliency guidance (ablation) | CoADNet-DR baseline · Cosal2015 | F-measure: 0.7402 -> 0.8023 | Helped |
| add OIaSG saliency guidance (ablation) | CoADNet-DR baseline · CoSOD3k | F-measure: 0.7099 -> 0.7489 | Helped |
| add GASA group-attentional aggregation (ablation) | CoADNet-DR baseline · CoSOD3k | F-measure: 0.7489 -> 0.8008 | Helped |
| add GASA group-attentional aggregation (ablation) | CoADNet-DR baseline · Cosal2015 | F-measure: 0.8023 -> 0.8465 | Helped |
| add GGD gated group distribution (ablation) | CoADNet-DR baseline · Cosal2015 | F-measure: 0.8465 -> 0.8682 | Helped |
| add GGD gated group distribution (ablation) | CoADNet-DR baseline · CoSOD3k | MAE: 0.0915 -> 0.0815 | Helped |
| replace deconvolution decoder with GCPD (ablation) | CoADNet-DR baseline · Cosal2015 | F-measure: 0.8682 -> 0.8874 | Helped |
| replace deconvolution decoder with GCPD (ablation) | CoADNet-DR baseline · CoSOD3k | MAE: 0.0815 -> 0.0652 | Helped |
| use stronger backbone (Dilated ResNet-50 vs ResNet-50) | CoADNet · MSRC | F-measure: 0.8710 -> 0.8618 | Hurt |
| use stronger backbone (Dilated ResNet-50 vs ResNet-50) | CoADNet · Cosal2015 | F-measure: 0.8771 -> 0.8874 | Helped |
| train on CoSOD3k (3316 images) instead of COCO-SEG | CoADNet-V · Cosal2015 | F-measure: 0.8748 -> 0.8592 | Hurt |
Closest papers by meaning
- Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking (CVPR 2023 · similarity 0.92)
- Taking a Deeper Look at Co-Salient Object Detection (CVPR 2020 · similarity 0.92)
- Group Collaborative Learning for Co-Salient Object Detection (CVPR 2021 · similarity 0.92)
- TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection (CVPR 2026 · similarity 0.91)
- CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection (CVPR 2024 · similarity 0.91)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.90)
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.