Research map / Image generation / GANs
Neural Characteristic Function Learning for Conditional Image Generation
Shengxi Li, Jialu Zhang, Yifei Li, Mai Xu, Xin Deng, Li Li
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 an auxiliary classifier to estimate p(y|x) instead of ground-truth labels (ablation) | CCF-GAN · CIFAR10 | FID: 7.48 -> 6.08 | Improved |
| use fixed linear ty in [-1, 1] rather than uniform or Gaussian random ty (ablation) | CCF-GAN · CIFAR10 | FID: 6.08 vs 7.05 (uniform), 7.07 (Gaussian) | Improved |
| vary fixed ty range alpha (0.5, 1, 10) (ablation) | CCF-GAN · CIFAR10 | FID: 6.51 / 6.08 / 7.02 | Mixed |
| increase number of projections k via NCF network (ablation) | CCF-GAN · CIFAR10 | FID | Improved |
| replace cross-entropy cGAN discriminator with neural characteristic function discriminator | BigGAN architecture · ImageNet 128x128 | FID / IS: FID 22.77 -> 11.34 (vs BigGAN); IS 180.84 vs 68.27 (ReACGAN) | Improved |
| replace cross-entropy cGAN discriminator with neural characteristic function discriminator | BigGAN architecture · VGGFace_c1000 | FID: 24.07 -> 5.70 | Improved |
| use CF-based discrepancy to reduce mode collapse and training instability | CCF-GAN · CIFAR10 / VGGFace_c1000 (precision-recall); 48 training conditions | precision, recall, successful trials | Improved |
Closest papers by meaning
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.90)
- Reciprocal GAN Through Characteristic Functions (RCF-GAN) (TPAMI 2022 · similarity 0.89)
- Reciprocal Adversarial Learning via Characteristic Functions (NeurIPS 2020 · similarity 0.89)
- Dual Projection Generative Adversarial Networks for Conditional Image Generation (ICCV 2021 · similarity 0.89)
- A Characteristic Function Approach to Deep Implicit Generative Modeling (CVPR 2020 · similarity 0.89)
- Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks (AAAI 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.
