Research map / Image generation / GANs
FEditNet: Few-Shot Editing of Latent Semantics in GAN Spaces
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 |
|---|---|---|---|
| Reuse the pretrained discriminator backbone as a frozen feature extractor for the attribute assessor (ablation) | FEditNet · StyleGAN2, Male editing | editing significance | Helped |
| Increase the feature contrastive loss weight (ablation) | FEditNet · StyleGAN2, Smile editing | attribute consistency | Helped |
| Increase the feature contrastive loss weight (ablation) | FEditNet · StyleGAN2, editing target attributes | editing significance | Hurt |
| Add layer-wise feature contrastive loss weight adjustment (ablation) | FEditNet · StyleGAN2, Age and Smile editing | attribute disentanglement | Helped |
| Use FEditNet instead of Latent2im | StyleGAN2 on FFHQ · FFHQ, Bangs editing | re-scoring score: 0.23 -> 0.38 | Helped |
| Use FEditNet instead of InterFaceGAN | StyleGAN2 on FFHQ · FFHQ, Male editing | re-scoring score: 0.17 -> 0.33 | Helped |
| Use FEditNet instead of Latent2im | StyleGAN2 on FFHQ · FFHQ, Smile editing | re-scoring score: 0.27 -> 0.30 | Helped |
| Use FEditNet instead of InterFaceGAN | StyleGAN2 on FFHQ · FFHQ, Young editing | re-scoring score: 0.17 -> 0.11 | Hurt |
Closest papers by meaning
- LARGE: Latent-Based Regression Through GAN Semantics (CVPR 2022 · similarity 0.91)
- Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020 · similarity 0.91)
- Closed-Form Factorization of Latent Semantics in GANs (CVPR 2021 · similarity 0.91)
- Navigating the GAN Parameter Space for Semantic Image Editing (CVPR 2021 · similarity 0.89)
- Editing in Style: Uncovering the Local Semantics of GANs (CVPR 2020 · similarity 0.89)
- NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models (CVPR 2024 · similarity 0.88)
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.