Research map / Image generation / Text-to-image diffusion
Semantic Image Synthesis via Adversarial Learning
Hao Dong, Simiao Yu, Chao Wu, Yike Guo
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 |
|---|---|---|---|
| use the proposed adversarial encoder-decoder with residual transformation instead of the baseline | Baseline · Caltech-200 birds pose | average rank: 2.87 -> 1.61 | Improved |
| use the proposed model instead of the baseline | Baseline · Caltech-200 birds background | average rank: 2.68 -> 1.93 | Improved |
| use the proposed model instead of the baseline | Baseline · Caltech-200 birds text match | average rank: 2.11 -> 1.94 | Improved |
| use the proposed model instead of the baseline | Baseline · Oxford-102 flowers shape | average rank: 2.97 -> 1.55 | Improved |
| use the proposed model instead of the baseline | Baseline · Oxford-102 flowers background | average rank: 2.62 -> 1.74 | Improved |
| use the proposed model instead of the baseline | Baseline · Oxford-102 flowers text match | average rank: 2.52 -> 1.75 | Improved |
| replace the learned encoder with a pretrained VGG encoder (ablation) | Ours · Caltech-200 birds background | average rank: 1.93 -> 1.39 | Improved |
| replace the learned encoder with a pretrained VGG encoder (ablation) | Ours · Caltech-200 birds pose | average rank: 1.61 -> 1.52 | Improved |
| replace the learned encoder with a pretrained VGG encoder (ablation) | Ours · Caltech-200 birds text match | average rank: 1.94 -> 1.95 | No clear effect |
| replace the learned encoder with a pretrained VGG encoder (ablation) | Ours · Oxford-102 flowers background | average rank: 1.74 -> 1.64 | Improved |
| replace the learned encoder with a pretrained VGG encoder (ablation) | Ours · Oxford-102 flowers text match | average rank: 1.75 -> 1.72 | No clear effect |
Closest papers by meaning
- Adversarial Learning of Semantic Relevance in Text to Image Synthesis (AAAI 2019 · similarity 0.91)
- Photographic Text-to-Image Synthesis With a Hierarchically-Nested Adversarial Network (CVPR 2018 · similarity 0.91)
- Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis (AAAI 2019 · similarity 0.91)
- You Only Need Adversarial Supervision for Semantic Image Synthesis (ICLR 2021 · similarity 0.91)
- DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022 · similarity 0.90)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (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.
