Research map / Label-efficient and robust learning / Semi-supervised learning
Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis
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 |
|---|---|---|---|
| use LCP-GAN (B) instead of Semi-BigGAN | BigGAN semi-supervised image synthesis · CUB-200 | FID: 24.4 -> 13.61 | Helped |
| use LCP-GAN (B) instead of Semi-BigGAN | BigGAN semi-supervised image synthesis · CUB-200 | RA: 64.52 -> 93.24 | Helped |
| use LCP-GAN (S) instead of Semi-StyleGAN | StyleGAN2-ADA semi-supervised image synthesis · CelebA-500 | FID: 16.23 -> 14.29 | Helped |
| use LCP-GAN (B) instead of Semi-BigGAN | BigGAN semi-supervised image synthesis · Dogs-120 | Intra-FID: 97.52 -> 72.06 | Helped |
| use LCP-GAN (B) instead of Semi-BigGAN | BigGAN semi-supervised image synthesis · ImageNet-1k | Intra-FID: 185.94 -> 142.15 | Helped |
| add class-level CLIP text similarity supervision (ablation) | Semi-BigGAN · CUB-200 | RA: 64.52 -> 88.58 | Helped |
| add class-level CLIP text similarity supervision (ablation) | Semi-BigGAN · Dogs-120 | Intra-FID: 97.52 -> 77.86 | Helped |
| condition on combinations of intra-class cluster embeddings (ablation) | Semi-BigGAN · CUB-200 | Intra-FID: 112.83 -> 108.38 | Helped |
| condition on combinations of intra-class cluster embeddings (ablation) | Semi-BigGAN · Dogs-120 | Intra-FID: 97.52 -> 82.83 | Helped |
| learn cluster context prompts rather than freezing them (ablation) | LCP-GAN (B) · CUB-200 | Intra-FID: 92.60 -> 88.03 | Helped |
| learn cluster context prompts rather than freezing them (ablation) | LCP-GAN (B) · CUB-200 | RA: 91.22 -> 93.24 | Helped |
| learn cluster context prompts rather than freezing them (ablation) | LCP-GAN (B) · Dogs-120 | Intra-FID: 74.75 -> 72.06 | Helped |
Closest papers by meaning
- Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis (CVPR 2021 · similarity 0.89)
- Conditional Image Synthesis with Auxiliary Classifier GANs (ICML 2017 · similarity 0.89)
- Improved Techniques for Training GANs (NeurIPS 2016 · similarity 0.89)
- Regularizing Discriminative Capability of CGANs for Semi-Supervised Generative Learning (CVPR 2020 · similarity 0.89)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.87)
- Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions (CVPR 2024 · similarity 0.87)
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.