# SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation

arXiv: https://arxiv.org/abs/2508.06429 · HTML: https://mlsanity.com/paper/2508.06429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Semi-Supervised Learning with Generative Adversarial Networks](https://mlsanity.com/paper/1606.01583/) (2016)
- [Good Semi-supervised Learning that Requires a Bad GAN](https://mlsanity.com/paper/1705.09783/) (2017)
- [The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better](https://mlsanity.com/paper/2406.05184/) (2024)
- [Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2311.11686/) (2023)
- [Triple Generative Adversarial Networks](https://mlsanity.com/paper/1912.09784/) (2019)
- [EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs](https://mlsanity.com/paper/2012.15864/) (2020)
- [MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network](https://mlsanity.com/paper/2006.06614/) (2020)
- [Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification](https://mlsanity.com/paper/2212.13589/) (2022)
- [Benchmarking Foundation Models and Parameter-Efficient Fine-Tuning for Prognosis Prediction in Medical Imaging](https://mlsanity.com/paper/2506.18434/) (2025)
- [Beyond the Generative Learning Trilemma: Generative Model Assessment in Data Scarcity Domains](https://mlsanity.com/paper/2504.10555/) (2025)

## Abstract (arXiv)

Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low labeled-data regimes, evaluated across settings with 5 to 50 labeled samples per class. Our approach integrates three specialized neural networks -- a generator for class-conditioned image translation, a discriminator for authenticity assessment and classification, and a dedicated classifier -- within a three-phase training framework. The method alternates between supervised training on limited labeled data and unsupervised learning that leverages abundant unlabeled images through image-to-image translation rather than generation from noise. We employ ensemble-based pseudo-labeling that combines confidence-weighted predictions from the discriminator and classifier with temporal consistency through exponential moving averaging, enabling reliable label estimation for unlabeled data. Comprehensive evaluation across eleven MedMNIST datasets demonstrates that our approach achieves statistically significant improvements over six state-of-the-art GAN-based semi-supervised methods, with particularly strong performance in the extreme 5-shot setting where the scarcity of labeled data is most challenging. The framework maintains its superiority across all evaluated settings (5, 10, 20, and 50 shots per class). Our approach offers a practical solution for medical imaging applications where annotation costs are prohibitive, enabling robust classification performance even with minimal labeled data. Code is available at https://github.com/GuidoManni/SPARSE.