Research map / Label-efficient and robust learning / Domain adaptation and generalization
Self-Mutating Network for Domain Adaptive Segmentation in Aerial Images
Kyungsu Lee, Haeyun Lee, Jae Youn Hwang
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 parameter mutation (GAN-based test-time tuning) to baseline (ablation) | SegNet baseline · Inria-trained to other domains | building IoU (%): 49.2 -> 52.8 | Improved |
| add parameter fluctuation to baseline (ablation) | SegNet baseline · Inria-trained to other domains | building IoU (%): 49.2 -> 52.9 | Improved |
| add parameter fluctuation on top of parameter mutation (ablation) | SMN · Inria-trained to other domains | building IoU (%): 52.8 -> 62.9 | Improved |
| add parameter mutation on top of parameter fluctuation (ablation) | SMN · Massachusetts-trained to other domains | building IoU (%): 52.4 -> 61.6 | Improved |
| generate similar-but-not-identical images (structural similarity weight) instead of identical (SAME) (ablation) | SMN · Inria-trained to other domains | building IoU (%): 52.2 -> 62.9 | Improved |
| generate similar-but-not-identical images instead of SAME, WHU-trained (ablation) | SMN · WHU-trained to other domains | building IoU (%): 53.2 -> 61.9 | Improved |
| SMN versus best domain-adaptation baseline, trained on Inria | SMN · Inria average mean IoU | mean IoU: 0.6193 -> 0.6290 | Improved |
| SMN versus best baseline, trained on OUD | SMN · OUD average mean IoU | mean IoU: 0.5973 -> 0.6086 | Improved |
| train on two domains rather than one | SMN · cross-domain building segmentation | IoU: 0.643 -> 0.717 | Improved |
Closest papers by meaning
- Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach (ICCV 2019 · similarity 0.86)
- Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision (CVPR 2020 · similarity 0.86)
- DAST: Unsupervised Domain Adaptation in Semantic Segmentation Based on Discriminator Attention and Self-Training (AAAI 2021 · similarity 0.85)
- Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation (AAAI 2021 · similarity 0.85)
- Domain Adaptive Semantic Segmentation With Self-Supervised Depth Estimation (ICCV 2021 · similarity 0.85)
- Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds (CVPR 2024 · similarity 0.84)
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.
