Research map / Detection and segmentation / Open-set and few-shot detection
Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation
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 pseudo-NIR images and two-branch network (SOD8s) (ablation) | FCN8s · Multi-spectral SOD, unsupervised | maxF (RGBN): 0.8194 -> 0.8200 | Helped |
| add adversarial domain adaptation (SOD8s+) (ablation) | SOD8s · Multi-spectral SOD, unsupervised | maxF (RGBN): 0.8200 -> 0.8458 | Helped |
| add adversarial domain adaptation (SOD8s+) (ablation) | SOD8s · Multi-spectral SOD, unsupervised | MAE (RGBN): 0.0700 -> 0.0611 | Helped |
| add adversarial domain adaptation (SOD16s+) (ablation) | SOD16s · Multi-spectral SOD, unsupervised | maxF (RGBN): 0.7773 -> 0.8093 | Helped |
| add pseudo-NIR two-branch network (SOD16s) (ablation) | FCN16s · Multi-spectral SOD, unsupervised | MAE (RGBN): 0.0984 -> 0.0996 | Mixed |
| use RGB+NIR pairs instead of RGB only | SOD8s+ · Multi-spectral SOD, unsupervised | maxF: 0.7966 -> 0.8458 | Helped |
| initialize fine-tuning from SOD8s+ instead of ImageNet VGG (ablation) | two-branch FCN8s · Multi-spectral SOD, supervised | maxF (RGBN): 0.8793 -> 0.9031 | Helped |
| initialize fine-tuning from SOD8s+ instead of SOD8s (ablation) | two-branch FCN8s · Multi-spectral SOD, supervised | maxF (RGBN): 0.8904 -> 0.9031 | Helped |
| initialize fine-tuning from SOD16s+ instead of SOD16s (ablation) | two-branch FCN16s · Multi-spectral SOD, supervised | maxF (RGBN): 0.8618 -> 0.8661 | Helped |
Closest papers by meaning
- DVSOD: RGB-D Video Salient Object Detection (NeurIPS 2023 · similarity 0.88)
- RGB-D Salient Object Detection via 3D Convolutional Neural Networks (AAAI 2021 · similarity 0.88)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.88)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.88)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.88)
- HSOD-BIT-V2: A Challenging Benchmark for Hyperspectral Salient Object Detection (AAAI 2025 · 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.