Research map / Image generation / Text-to-image diffusion
Dual Adversarial Inference for Text-to-Image Synthesis
Qicheng Lao, Mohammad Havaei, Ahmad Pesaranghader, Francis Dutil, Lisa Di Jorio, Thomas Fevens
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 dual adversarial inference (content and style) to HDGAN | HDGAN · Oxford-102 64x64 | FID: 40.02 -> 37.94 | Improved |
| add dual adversarial inference to HDGAN | HDGAN · CUB 64x64 | FID: 20.60 -> 18.41 | Improved |
| add dual adversarial inference to HDGAN | HDGAN · COCO 64x64 | FID: 29.13 -> 27.07 | Improved |
| add dual adversarial inference to HDGAN | HDGAN · COCO 64x64 | Inception score: 8.64 -> 8.94 | Improved |
| add dual adversarial inference to HDGAN | HDGAN · CUB 64x64 | Inception score: 3.58 -> 3.58 | No clear effect |
| add dual adversarial inference to HDGAN | HDGAN · Oxford-102 64x64 | Inception score: 2.90 -> 2.90 | No clear effect |
| add dual adversarial inference to HDGAN | HDGAN · CUB 64x64 | Visual-semantic similarity: 0.263 -> 0.251 | No clear effect |
| add V_t2i matching-aware discriminator (ablation) | Ours · CUB 64x64 | FID: 20.65 -> 18.41 | Improved |
| add V_t2i matching-aware discriminator (ablation) | Ours · CUB 64x64 | Inception score: 3.31 -> 3.58 | Improved |
| add adversarial cycle-consistency V_cycle (ablation) | Ours · CUB 64x64 | FID: 19.29 -> 18.41 | Improved |
| add adversarial cycle-consistency V_cycle (ablation) | Ours · CUB 64x64 | Inception score: 3.53 -> 3.58 | Improved |
| use adversarial loss rather than l2 loss for cycle-consistency (ablation) | Ours · CUB 64x64 | FID: 149.8 -> 18.41 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StackGAN — StackGAN: Text to Photo-Realistic Image Synthesis With Stacked Generative Adversarial Networks (ICCV 2017) · 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
- Semantic Image Synthesis via Adversarial Learning (ICCV 2017 · similarity 0.90)
- CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis (ECCV 2020 · similarity 0.89)
- Adversarial Learning of Semantic Relevance in Text to Image Synthesis (AAAI 2019 · similarity 0.89)
- StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis (ICML 2023 · similarity 0.89)
- DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022 · similarity 0.89)
- Text to Image Generation With Semantic-Spatial Aware GAN (CVPR 2022 · 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.
