Research map / Image generation / GANs
WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation
Mengping Yang, Zhe Wang, Ziqiu Chi, Wenyi Feng
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 high-frequency skip connection (ablation) | WaveGAN-B · Flower (3-shot) | FID: 85.25 -> 42.17 | Improved |
| add high-frequency skip connection (ablation) | WaveGAN-B · Animal Faces (3-shot) | FID: 108.82 -> 30.35 | Improved |
| add high-frequency skip connection (ablation) | WaveGAN-B · VGGFace (3-shot) | FID: 20.61 -> 4.96 | Improved |
| add high-frequency skip connection (ablation) | WaveGAN-M · Flower (3-shot) | FID: 87.99 -> 63.79 | Improved |
| add low-frequency skip connection (ablation) | WaveGAN-B · Flower (3-shot) | FID: 44.31 -> 42.17 | Improved |
| add low-frequency skip connection (ablation) | WaveGAN-M · Flower (3-shot) | FID: 72.35 -> 63.79 | Improved |
| add frequency L1 loss (ablation) | WaveGAN-B · Flower (3-shot) | FID: 45.52 -> 42.17 | Improved |
| add frequency L1 loss (ablation) | WaveGAN-M · Animal Faces (3-shot) | FID: 62.13 -> 50.98 | Improved |
| add local fusion (LoF) module (ablation) | WaveGAN-B · Flower (3-shot) | FID: 47.37 -> 42.17 | Improved |
| add local fusion (LoF) module (ablation) | WaveGAN-M · Flower (3-shot) | FID: 82.18 -> 63.79 | Improved |
| feed all high-frequency components (LH,HL,HH) instead of only one (ablation) | WaveGAN-M · Flower (3-shot) | FID: 69.73 -> 63.79 | Improved |
| feed all high-frequency components instead of only HH (ablation) | WaveGAN-B · Flower (3-shot) | FID: 42.75 -> 42.17 | Improved |
Closest papers by meaning
- Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis (ICLR 2021 · similarity 0.89)
- FreGAN: Exploiting Frequency Components for Training GANs under Limited Data (NeurIPS 2022 · similarity 0.89)
- WeditGAN: Few-Shot Image Generation via Latent Space Relocation (AAAI 2024 · similarity 0.88)
- A Closer Look at Few-Shot Image Generation (CVPR 2022 · similarity 0.87)
- Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile (AAAI 2024 · similarity 0.86)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (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.
