Research map / Image generation / GANs
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis
Check 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 |
|---|---|---|---|
| Add dynamic memory (ablation) | DM-GAN baseline · CUB | IS: 4.51$\pm$0.04 -> 4.57$\pm$0.05 | Helped |
| Add dynamic memory (ablation) | DM-GAN baseline · CUB | FID: 23.32 -> 21.41 | Helped |
| Add dynamic memory (ablation) | DM-GAN baseline · CUB | R-precision: 68.60$\pm$0.73 -> 70.66$\pm$0.69 | Helped |
| Add memory writing gate (ablation) | DM-GAN with dynamic memory · CUB | IS: 4.57$\pm$0.05 -> 4.65$\pm$0.05 | Helped |
| Add memory writing gate (ablation) | DM-GAN with dynamic memory · CUB | FID: 21.41 -> 20.83 | Helped |
| Add memory writing gate (ablation) | DM-GAN with dynamic memory · CUB | R-precision: 70.66$\pm$0.69 -> 71.40$\pm$0.64 | Helped |
| Add response gate (ablation) | DM-GAN with dynamic memory and memory writing gate · CUB | IS: 4.65$\pm$0.05 -> 4.75$\pm$0.07 | Helped |
| Add response gate (ablation) | DM-GAN with dynamic memory and memory writing gate · CUB | FID: 20.83 -> 16.09 | Helped |
| Add response gate (ablation) | DM-GAN with dynamic memory and memory writing gate · CUB | R-precision: 71.40$\pm$0.64 -> 72.31$\pm$0.91 | Helped |
| Replace AttnGAN with DM-GAN | Text-to-image synthesis · CUB | IS: 4.36 -> 4.75 | Helped |
| Replace AttnGAN with DM-GAN | Text-to-image synthesis · COCO | IS: 25.89 -> 30.49 | Helped |
| Replace AttnGAN with DM-GAN | Text-to-image synthesis · CUB | FID: 23.98 -> 16.09 | Helped |
Closest papers by meaning
- DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022 · similarity 0.92)
- Generative Adversarial Text to Image Synthesis (ICML 2016 · similarity 0.90)
- Adversarial Text to Continuous Image Generation (CVPR 2024 · similarity 0.90)
- StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis (ICML 2023 · similarity 0.90)
- Adversarial Learning of Semantic Relevance in Text to Image Synthesis (AAAI 2019 · similarity 0.89)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 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.