Research map / Label-efficient and robust learning / Test-time adaptation
Test-time Domain Generalization for Image Super-resolution
Zaizuo Tang, Yu-Bin Yang
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 domain-invariant codebook next to domain-specific codebooks (ablation) | MC-TTDG · DRealSR Sony | PSNR: 31.0144 -> 31.2937 | Improved |
| use multiple domain codebooks instead of one codebook (ablation) | MC-TTDG · DRealSR Sony | PSNR: 31.1411 -> 31.2937 | Improved |
| use codebook-based pixel-level transfer instead of multi-center style transfer (ablation) | MC-TTDG · DRealSR Sony | PSNR: 30.7166 -> 31.2937 | Improved |
| use voting selection instead of max predicted score (ablation) | MC-TTDG · DRealSR Sony | PSNR: 30.6124 -> 31.2937 | Improved |
| use voting selection instead of max predicted score (Top1 accuracy) (ablation) | MC-TTDG · DRealSR Sony | Top1 accuracy: 0.0596 -> 0.3545 | Improved |
| use voting selection instead of minimum-distance codeword (ablation) | MC-TTDG · DRealSR Pan | PSNR: 31.0203 -> 31.1571 | Improved |
| add domain-specific features (ablation) | MC-TTDG · DRealSR Pan | PSNR: 30.3096 -> 31.1571 | Improved |
| add transfer of domain-specific features (ablation) | MC-TTDG · DRealSR Pan | PSNR: 30.9597 -> 31.1571 | Improved |
| use implicit codebook separation instead of Fourier transform separation (ablation) | MC-TTDG · DRealSR DSC | PSNR: 30.1373 -> 31.2118 | Improved |
| use implicit codebook separation instead of wavelet separation (ablation) | MC-TTDG · DRealSR Sony | PSNR: 31.0207 -> 31.2937 | Improved |
| increase domain-specific codebooks from 1 to 5 (ablation) | MC-TTDG · DRealSR Sony | PSNR: 31.0125 -> 31.3129 | Improved |
| increase codewords from 128 to 512 (ablation) | MC-TTDG · DRealSR Sony | PSNR: 31.1052 -> 31.3001 | Improved |
Closest papers by meaning
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.86)
- START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation (NeurIPS 2024 · similarity 0.85)
- Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap (ICLR 2025 · similarity 0.84)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.84)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.84)
- IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution (NeurIPS 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.
