Research map / Image generation / Text-to-image diffusion
DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image Synthesis
Shulan Ruan, Yong Zhang, Kun Zhang, Yanbo Fan, Fan Tang, Qi Liu, Enhong Chen
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 Attended Global Refinement (AGR) (ablation) | DAE-GAN · COCO | FID: 149.79 -> 28.12 | Improved |
| add Attended Global Refinement (AGR) (ablation) | DAE-GAN · COCO | Inception Score: 2.93 -> 35.08 | Improved |
| add Attended Global Refinement (AGR) (ablation) | DAE-GAN · COCO | R-precision: 2.34 -> 92.61 | Improved |
| add Aspect-aware Local Refinement (ALR) (ablation) | DAE-GAN · COCO | FID: 32.93 -> 28.12 | Improved |
| add Aspect-aware Local Refinement (ALR) (ablation) | DAE-GAN · COCO | Inception Score: 31.07 -> 35.08 | Improved |
| add Aspect-aware Local Refinement (ALR) (ablation) | DAE-GAN · COCO | R-precision: 90.24 -> 92.61 | Improved |
| add aspect information to AGR (ablation) | DAE-GAN · COCO | FID: 28.60 -> 28.12 | Improved |
| add aspect information to AGR (ablation) | DAE-GAN · COCO | Inception Score: 34.70 -> 35.08 | Improved |
| add aspect information to AGR (ablation) | DAE-GAN · COCO | R-precision: 92.28 -> 92.61 | Improved |
| DAE-GAN versus strongest prior method on IS | DAE-GAN · CUB-200 | Inception Score: 5.23 vs 4.42 | Hurt |
| DAE-GAN versus best prior FID | DAE-GAN · CUB-200 | FID: 16.09 -> 15.19 | Improved |
| DAE-GAN versus best prior R-precision | DAE-GAN · CUB-200 | R-precision (%): 72.31 -> 85.45 | Improved |
Later papers that compared with this method
1 later accepted paper reports DAE-GAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis (CVPR 2022 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DM-GAN — DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (CVPR 2019) · better on 5 of 6 shared results
- AttnGAN — AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks (CVPR 2018) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Text to Image Generation With Semantic-Spatial Aware GAN (CVPR 2022 · similarity 0.91)
- DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (CVPR 2019 · similarity 0.91)
- Adversarial Text to Continuous Image Generation (CVPR 2024 · similarity 0.87)
- Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation (AAAI 2024 · similarity 0.87)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.87)
- 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.
