Research map / Label-efficient and robust learning / Semi-supervised learning
GAN-based semi-supervised learning
Uses generative adversarial models and perturbation regularization to exploit unlabeled data.
61 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Semi-supervised learning, keyword cluster “semi · examples · classification”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
4 papers in 2023–24 and 7 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 2.5% to 4.4%.
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
- 2016 · Improved Techniques for Training GANs (NeurIPS 2016 · 1,344 citations)
- 2017 · Good Semi-supervised Learning That Requires a Bad GAN (NeurIPS 2017 · 229 citations)
- 2018 · Learning to Localize Sound Source in Visual Scenes (CVPR 2018 · 349 citations)
- 2019 · Semi-Supervised Transfer Learning for Image Rain Removal (CVPR 2019 · 476 citations)
- 2020 · A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (CVPR 2020 · 167 citations)
- 2021 · What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels (CVPR 2021 · 105 citations)
- 2022 · Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer (CVPR 2022 · 22 citations)
- 2023 · Semi-supervised Deep Large-Baseline Homography Estimation with Progressive Equivalence Constraint (AAAI 2023 · 20 citations)
- 2024 · A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint (CVPR 2024 · 74 citations)
- 2025 · Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · 1 citation)
- 2026 · Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations (ICML 2026 · 0 citations)
Earliest papers here
- Improved Techniques for Training GANs (NeurIPS 2016 · 1,344 citations)
- Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning (NeurIPS 2016 · 546 citations)
- Good Semi-supervised Learning That Requires a Bad GAN (NeurIPS 2017 · 229 citations)
What has been tried
54 papers here report 616 measured changes (a component added, removed or swapped, compared with a baseline): helped 72%, no clear effect 5%, hurt 22%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add frequency domain projection to SFII | UNREAL-NH · SSIM | 0.848 -> 0.862 | Helped | A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint (CVPR 2024 · 74 citations) |
| Add OGS samples to 10% synthetic training data | Union14M-Benchmark · AVG accuracy | 58.2 -> 60.3 | Helped | Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing (NeurIPS 2024 · 3 citations) |
| Add chromatic and spatial uneven perturbations | NUDT-SIRST 1/8 labeled · IoU (%) | 79.61 -> 85.07 | Helped | Semi-supervised Infrared Small Target Detection with Thermodynamic-Inspired Uneven Perturbation and Confidence Adaptation (AAAI 2025 · 1 citation) |
| add supervised visibility augmentations | EHT Dataset · PSNR (dB) | 21.36 -> 21.89 | Helped | VisRec: A Semi-Supervised Approach to Visibility Data Reconstruction in Radio Astronomy (AAAI 2025 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 28 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
- Holistic semi-supervised pipelines (125 papers)
- Self-training theory (86 papers)
- Safe and realistic semi-supervised learning (70 papers)
Elsewhere in the topic
- Confidence-based pseudo-label selection (134 papers)
- Semi-supervised medical segmentation (50 papers)
- Consistency training for semi-supervised segmentation (49 papers)
- Pseudo-labeling for specialized tasks (48 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).