Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Single-Stage Controllable GANs for Conditional Fine-Grained Image Generation
Tianyi Chen, Yi Liu, Yunfei Zhang, Si Wu, Yong Xu, Feng Liangbing, Hau San Wong
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 class-semantic regularization (ablation) | Baseline · CUB | RA: 11.04 -> 90.43 | Improved |
| add class-semantic regularization (ablation) | Baseline · CUB | FID: 82.87 -> 50.35 | Improved |
| add Dxb discriminator and b-based regularization (ablation) | Baseline + class-semantic reg. · CUB | FID: 50.35 -> 30.48 | Improved |
| add Dxb discriminator and b-based regularization (ablation) | Baseline + class-semantic reg. · CUB | cFID: 157.97 -> 113.42 | Improved |
| add encoder M and x~-based regularization (ablation) | Baseline + class-semantic + Dxb · CUB | FID: 30.48 -> 20.03 | Improved |
| add encoder M and x~-based regularization (ablation) | Baseline + class-semantic + Dxb · CUB | RA: 92.49 -> 97.85 | Improved |
| add all SSC-GAN components to baseline (ablation) | Baseline · CUB | IS: 4.42 -> 4.68 | Improved |
| add all SSC-GAN components to baseline | Baseline · FS-100 | FID: 30.63 -> 20.65 | Improved |
| add all SSC-GAN components to baseline | Baseline · Stanford-Cars | FID: 50.78 -> 39.02 | Improved |
| use full supervision instead of semi-supervised labels | SSC-GAN · CUB | FID: 20.03 -> 18.34 | Improved |
| use full supervision instead of semi-supervised labels | SSC-GAN · FS-100 | FID: 20.65 -> 16.28 | Improved |
| use full supervision instead of semi-supervised labels | SSC-GAN · Stanford-Cars | FID: 39.02 -> 37.48 | Improved |
Closest papers by meaning
- Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis (CVPR 2023 · similarity 0.90)
- OSSGAN: Open-Set Semi-Supervised Image Generation (CVPR 2022 · similarity 0.90)
- Semi-supervised FusedGAN for Conditional Image Generation (ECCV 2018 · similarity 0.90)
- Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis (CVPR 2021 · similarity 0.90)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.89)
- Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation (AAAI 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.
