Research map / Detection and segmentation / CNN features
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object 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 CPFP instead of PCF | RGBD salient object detection · SSB1000 | mean F-measure: 0.818 -> 0.842 | Helped |
| Use CPFP instead of PCF | RGBD salient object detection · NJU2000 | mean F-measure: 0.840 -> 0.850 | Helped |
| Use CPFP instead of PCF | RGBD salient object detection · LFSD | mean F-measure: 0.761 -> 0.811 | Helped |
| Use CPFP instead of PCF | RGBD salient object detection · RGBD135 | mean F-measure: 0.765 -> 0.815 | Helped |
| Use CPFP instead of PCF | RGBD salient object detection · NLPR | mean F-measure: 0.809 -> 0.840 | Helped |
| Add a contrast-enhanced net for depth information (ablation) | VGG-16 RGBD detector · NJU2000 | mean F-measure: 0.714 -> 0.756 | Helped |
| Use the original depth map directly instead of contrast-enhancing it (ablation) | VGG-16 RGBD detector · NJU2000 | mean F-measure: 0.714 -> 0.708 | Hurt |
| Add fluid pyramid integration to the contrast-enhanced model (ablation) | VGG-16 RGBD detector · NJU2000 | mean F-measure: 0.756 -> 0.851 | Helped |
| Replace fluid pyramid integration with direct multi-scale fusion (ablation) | VGG-16 RGBD detector with contrast enhancement · NJU2000 | mean F-measure: 0.851 -> 0.748 | Hurt |
| Replace fluid pyramid integration with traditional pyramid fusion (ablation) | VGG-16 RGBD detector with contrast enhancement · NJU2000 | mean F-measure: 0.851 -> 0.789 | Hurt |
| Use original depth rather than contrast enhancement while retaining fluid pyramid integration (ablation) | VGG-16 RGBD detector · NJU2000 | mean F-measure: 0.783 -> 0.851 | Hurt |
| Add fluid pyramid integration without the contrast-enhanced net (ablation) | VGG-16 RGBD detector · NJU2000 | mean F-measure: 0.714 -> 0.758 | Helped |
Closest papers by meaning
- RGB-D Salient Object Detection via 3D Convolutional Neural Networks (AAAI 2021 · similarity 0.90)
- Calibrated RGB-D Salient Object Detection (CVPR 2021 · similarity 0.90)
- Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR 2021 · similarity 0.90)
- Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (CVPR 2018 · similarity 0.90)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.88)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.87)
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.