Research map / Detection and segmentation / CNN features
Summarize and Search: Learning Consensus-Aware Dynamic Convolution for Co-Saliency Detection
Ni Zhang, Junwei Han, Nian Liu, Ling Shao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 vanilla adaptive kernels (ablation) | baseline · CoCA | max F-measure: 0.451 -> 0.495 | Improved |
| add vanilla common kernel (ablation) | baseline · CoCA | max F-measure: 0.451 -> 0.497 | Improved |
| use large 3x3 adaptive kernels instead of 1x1 (ablation) | CADC · CoCA | max F-measure: 0.495 -> 0.508 | Improved |
| use large 3x3 common kernel instead of 1x1 (ablation) | CADC · CoCA | max F-measure: 0.497 -> 0.498 | Improved |
| combine large adaptive and common kernels (ablation) | CADC · CoCA | max F-measure: 0.508 -> 0.511 | Improved |
| add multi-level dynamic convolution in first four decoders (ablation) | CADC · CoCA | max F-measure: 0.511 -> 0.548 | Improved |
| add multi-level dynamic convolution (ablation) | CADC · CoCA | MAE: 0.144 -> 0.132 | Improved |
| add original DUTS class data to COCO-sub training (ablation) | CADC · CoCA | max F-measure: 0.467 -> 0.494 | Improved |
| add normal synthesis only (ablation) | CADC · CoCA | max F-measure: 0.494 -> 0.504 | Improved |
| add reverse synthesis only (ablation) | CADC · CoCA | max F-measure: 0.494 -> 0.510 | Improved |
| use bidirectional (normal + reverse) synthesis (ablation) | CADC · CoCA | max F-measure: 0.504 -> 0.548 | Improved |
| replace jigsaw synthesis with bidirectional copy-and-blend synthesis (ablation) | CADC · CoCA | max F-measure: 0.537 -> 0.548 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ICNet — ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CADC++: Advanced Consensus-Aware Dynamic Convolution for Co-Salient Object Detection (TPAMI 2023 · similarity 0.94)
- Memory-Aided Contrastive Consensus Learning for Co-salient Object Detection (AAAI 2023 · similarity 0.90)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.89)
- Robust Deep Co-Saliency Detection with Group Semantic (AAAI 2019 · similarity 0.89)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.88)
- Spotting the Unseen: Reciprocal Consensus Network Guided by Visual Archetypes (AAAI 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.
