Research map / Detection and segmentation / Open-set and few-shot detection
Few-Cost Salient Object Detection with Adversarial-Paced Learning
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 |
|---|---|---|---|
| Use FC-SOD with 1k annotated training images instead of fully supervised F3NET | Salient object detection · DUTS-TE | F_max: 0.897 -> 0.846 | Hurt |
| Use FC-SOD with 1k annotated training images instead of fully supervised PoolNet | Salient object detection · PASCAL-S | F_max: 0.884 -> 0.848 | Hurt |
| Use FC-SOD with 1k annotated training images instead of fully supervised EGNet | Salient object detection · DUT-O | F_max: 0.842 -> 0.767 | Hurt |
| Use FC-SOD with 1k annotated training images instead of fully supervised EGNet | Salient object detection · SOD | F_max: 0.889 -> 0.846 | Hurt |
| Add adversarial-paced pseudo-label weighting to labeled-only training (ablation) | FC-SOD · DUTS-TE | F_max: 0.817 -> 0.846 | Helped |
| Add adversarial-paced pseudo-label weighting to labeled-only training (ablation) | FC-SOD · DUT-O | F_max: 0.719 -> 0.767 | Helped |
| Add adversarial pace loss (ablation) | FC-SOD · DUTS-TE | F_max: 0.822 -> 0.846 | Helped |
| Add adversarial pace loss (ablation) | FC-SOD · DUT-O | F_max: 0.736 -> 0.767 | Helped |
| Refine generated pseudo-labels with GrabCut (ablation) | FC-SOD · DUTS-TE | F_max: 0.846 -> 0.730 | Hurt |
| Replace global structure-guided weighting with conventional pixel GAN (ablation) | FC-SOD · DUT-O | F_max: 0.754 -> 0.767 | Hurt |
| Add ground-truth pixel-wise reliability supervision (ablation) | FC-SOD · DUT-O | F_max: 0.752 -> 0.767 | Helped |
| Replace adversarial-paced learning with conventional SPL regularizers (ablation) | FC-SOD · DUTS-TE | F_max: 0.817 -> 0.846 | Hurt |
Closest papers by meaning
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.88)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.88)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.88)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- Exploring Salient Object Detection with Adder Neural Networks (AAAI 2025 · similarity 0.86)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · similarity 0.85)
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.