Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images through Generative Latent Search
Prashant Pandey, Aayush Kumar Tyagi, Sameer Ambekar, Prathosh AP
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 Sobel edge concatenation to decoder (ablation) | GLSS (perceptual loss + latent search) · SNV (DeepLabv3+) | IoU: 0.182 -> 0.385 | Improved |
| add Sobel edge concatenation to decoder (ablation) | GLSS (perceptual loss + latent search) · Hand Gesture (DeepLabv3+) | IoU: 0.300 -> 0.698 | Improved |
| add perceptual loss (ablation) | GLSS (edge + latent search) · SNV (DeepLabv3+) | IoU: 0.223 -> 0.385 | Improved |
| add perceptual loss (ablation) | GLSS (edge + latent search) · Hand Gesture (DeepLabv3+) | IoU: 0.58 -> 0.698 | Improved |
| add latent search (ablation) | GLSS (edge + perceptual loss) · SNV (DeepLabv3+) | IoU: 0.330 -> 0.385 | Improved |
| add latent search (ablation) | GLSS (edge + perceptual loss) · Hand Gesture (DeepLabv3+) | IoU: 0.615 -> 0.698 | Improved |
| add edge concatenation alone to baseline (ablation) | GLSS baseline · Hand Gesture (DeepLabv3+) | IoU: 0.227 -> 0.560 | Improved |
| add latent search alone (ablation) | GLSS baseline · SNV (DeepLabv3+) | IoU: 0.112 -> 0.128 | Improved |
| use VAE instead of BigGAN as generative model (ablation) | GLSS · SNV (DeepLabv3+) | IoU: 0.09 -> 0.38 | Improved |
| use VAE instead of BigGAN as generative model (ablation) | GLSS · Hand Gesture (DeepLabv3+) | IoU: 0.21 -> 0.69 | Improved |
| reduce target data used for VAE training from 60% to 20% | GLSS · SNV target-independence | IoU: 0.37 -> 0.38 | No clear effect |
| reduce target data used from 60% to 20% | DADA · SNV target-independence | IoU: 0.31 -> 0.23 | Hurt |
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.
- DADA — DADA: Depth-Aware Domain Adaptation in Semantic Segmentation (ICCV 2019) · better on 4 of 4 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
- Reducing Domain Gap in Frequency and Spatial Domain for Cross-Modality Domain Adaptation on Medical Image Segmentation (AAAI 2023 · similarity 0.87)
- FDA: Fourier Domain Adaptation for Semantic Segmentation (CVPR 2020 · similarity 0.86)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.86)
- I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation (TPAMI 2022 · similarity 0.86)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.85)
- UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation (ICLR 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.
