Research map / Image generation / GANs
Conditional GANs
Improve conditional image synthesis with diversity and contrastive objectives.
25 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2024) · an approach in GANs, keyword cluster “synthesis · latent · face”
State History Benchmarks Tried Baselines Preprints Export
Where it stands
Quiet None of the tracked benchmarks has a report from 2025–26.
1 papers in 2023–24 and 0 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.7% to 0.0%.
Open questions the data points to
- Papers report BicycleGAN on Maps (LPIPS) anywhere from 0.115 to 0.247: comparisons against it depend on whose number you take.
- Papers report BicycleGAN on Maps (FID) anywhere from 130.74 to 145.78: comparisons against it depend on whose number you take.
No longer reported by papers here: CIFAR10 (FID, last in 2021).
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Conditional Image Synthesis with Auxiliary Classifier GANs (ICML 2017 · 2,029 citations)
- 2018 · High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs (CVPR 2018 · 4,515 citations)
- 2019 · Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis (CVPR 2019 · 437 citations)
- 2020 · CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks (CVPR 2020 · 220 citations)
- 2021 · Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (ICLR 2021 · 135 citations)
- 2022 · CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis (NeurIPS 2022 · 0 citations)
- 2024 · Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation (AAAI 2024 · 5 citations)
Earliest papers here
- Conditional Image Synthesis with Auxiliary Classifier GANs (ICML 2017 · 2,029 citations)
- Generative Attribute Controller With Conditional Filtered Generative Adversarial Networks (CVPR 2017 · 97 citations)
- Structured Generative Adversarial Networks (NeurIPS 2017 · 51 citations)
Benchmark records
The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.
CIFAR10 · FID (lower is better)
4 papers, 2018–2021 · not reported since 2021
| Year | Best so far | Set by |
|---|---|---|
| 2018 | 17.5 | cGANs with Projection Discriminator (ICLR 2018 · 407 citations) |
| 2020 | 10.6 | ContraGAN: Contrastive Learning for Conditional Image Generation (NeurIPS 2020 · 94 citations) |
What has been tried
25 papers here report 283 measured changes (a component added, removed or swapped, compared with a baseline): helped 73%, no clear effect 4%, hurt 20%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use noise truncation instead of PGD truncation | Conditional image generation · Visual plausibility | Helped | Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation (AAAI 2024 · 5 citations) |
Baseline numbers that disagree
The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.
| Baseline | Benchmark | Metric | Reported | Papers |
|---|---|---|---|---|
| BicycleGAN | Maps | LPIPS | 0.115 – 0.247 | 2 papers, e.g. CVPR 2019 and CVPR 2021 |
| BicycleGAN | Maps | FID | 130.74 – 145.78 | 2 papers, e.g. CVPR 2021 and CVPR 2019 |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 20 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Large-scale GAN latent analysis (108 papers)
- GAN-based image manipulation (90 papers)
- GAN vocoders and audio synthesis (13 papers)
Elsewhere in the topic
- Stabilized GAN training (144 papers)
- Generative adversarial network theory (62 papers)
- GAN latent optimization and evaluation (52 papers)
- GANs for text generation (21 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).