Research map / Label-efficient and robust learning / Test-time adaptation
Target-Aware Generative Augmentations for Single-Shot 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 |
|---|---|---|---|
| Single-shot StyleGAN fine-tuning with prune-zero sampling (SiSTA) as augmentation for NRC adaptation | DomainNet Real->QuickDraw · DomainNet QuickDraw | accuracy: 9.23 -> 13.12 | Helped |
| Single-shot SiSTA prune-zero augmentation | DomainNet Real->Sketch · DomainNet Sketch | accuracy: 43.86 -> 48.12 | Helped |
| Toolbox augmentation (Augmix/RandConv) within MEMO | DomainNet Real->QuickDraw · DomainNet QuickDraw | accuracy: 9.23 -> 8.73 (Augmix), 8.04 (RandConv) | Hurt |
| Prune-zero vs base sampling for SiSTA on DomainNet (ablation) | SiSTA sampling · DomainNet QuickDraw and Sketch | accuracy: QuickDraw 11.78 -> 13.12; Sketch 47.54 -> 48.12; Painting 63.53 -> 63.69 vs base | Mixed |
| Prune-zero sampling vs MEMO on CelebA Domain C | SiSTA sampling · CelebA-HQ Domain C | accuracy: Bangs 58.2 source-only -> 82.6 prune-zero, MEMO (Augmix) 61.6 | Helped |
| Prune-zero sampling on CelebA Domain A (gender) | SiSTA sampling · CelebA-HQ Domain A | accuracy: 93.2 -> 95.5 | Helped |
| Toolbox augmentations (Augmix) added to MEMO on CelebA Domain C | MEMO · CelebA-HQ Domain C | accuracy: Bangs 58.2 -> 61.6; Bald 50.1 -> 50.2 | Mixed |
| Prune-zero sampling on CelebA Domain D (Fog) | SiSTA sampling · CelebA-HQ Domain D Fog | accuracy (Bangs): Bangs 59.9 source -> 86.7? | Helped |
Closest papers by meaning
- One-Shot Domain Adaptation for Face Generation (CVPR 2020 · similarity 0.89)
- On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning? (CVPR 2024 · similarity 0.87)
- Preventing Shortcuts in Adapter Training via Providing the Shortcuts (NeurIPS 2025 · similarity 0.86)
- AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition (NeurIPS 2025 · similarity 0.86)
- Provably Improving Generalization of Few-shot models with Synthetic Data (ICML 2025 · similarity 0.86)
- A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models (CVPR 2024 · 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.