# Collapse by Conditioning: Training Class-conditional GANs with Limited Data

arXiv: https://arxiv.org/abs/2201.06578 · HTML: https://mlsanity.com/paper/2201.06578/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 28 of 28)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [Efficient Conditional GAN Transfer with Knowledge Propagation across Classes](https://mlsanity.com/paper/2102.06696/) (2021)
- [On Leveraging Pretrained GANs for Generation with Limited Data](https://mlsanity.com/paper/2002.11810/) (2020)
- [Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution](https://mlsanity.com/paper/2111.03649/) (2021)
- [Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation](https://mlsanity.com/paper/1902.09225/) (2019)
- [Rethinking conditional GAN training: An approach using geometrically structured latent manifolds](https://mlsanity.com/paper/2011.13055/) (2020)

## Built on by (most cited first, 25 of 25)

- [A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials](https://mlsanity.com/paper/2205.05467/) (2022)
- [Fill-Up: Balancing Long-Tailed Data with Generative Models](https://mlsanity.com/paper/2306.07200/) (2023)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs](https://mlsanity.com/paper/2304.05866/) (2023)
- [Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions](https://mlsanity.com/paper/2402.17065/) (2024)
- [DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data](https://mlsanity.com/paper/2211.14694/) (2022)
- [Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation](https://mlsanity.com/paper/2311.08217/) (2023)
- [Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning](https://mlsanity.com/paper/2503.00639/) (2025)
- [Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances](https://mlsanity.com/paper/2310.13433/) (2023)
- [ACQ: Improving Generative Data-free Quantization Via Attention Correction](https://mlsanity.com/paper/2301.07266/) (2023)
- [StyleGenes: Discrete and Efficient Latent Distributions for GANs](https://mlsanity.com/paper/2305.00599/) (2023)
- [Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks](https://mlsanity.com/paper/2312.03443/) (2023)
- [Content-Style Learning from Unaligned Domains: Identifiability under Unknown Latent Dimensions](https://mlsanity.com/paper/2411.03755/) (2024)
- [Content-Style Identification via Differential Independence](https://mlsanity.com/paper/2605.17827/) (2026)
- [Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation](https://mlsanity.com/paper/2303.05240/) (2023)
- [DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion](https://mlsanity.com/paper/2305.14849/) (2023)
- [Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model](https://mlsanity.com/paper/2507.09052/) (2025)
- [ResBit: Residual Bit Vector for Categorical Values](https://mlsanity.com/paper/2309.17196/) (2023)
- [One Style is All you Need to Generate a Video](https://mlsanity.com/paper/2310.17835/) (2023)
- [Medical Speech Symptoms Classification via Disentangled Representation](https://mlsanity.com/paper/2403.05000/) (2024)
- [Wind Power Scenario Generation based on the Generalized Dynamic Factor Model and Generative Adversarial Network](https://mlsanity.com/paper/2508.00692/) (2025)
- [Pairing Regularization for Mitigating Many-to-One Collapse in GANs](https://mlsanity.com/paper/2604.20130/) (2026)
- [Image Tokenizers Should Be Trained Between Images](https://mlsanity.com/paper/2610.16759/) (2026)

## Abstract (arXiv)

Class-conditioning offers a direct means to control a Generative Adversarial Network (GAN) based on a discrete input variable. While necessary in many applications, the additional information provided by the class labels could even be expected to benefit the training of the GAN itself. On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability. Motivated by this observation, we propose a training strategy for class-conditional GANs (cGANs) that effectively prevents the observed mode-collapse by leveraging unconditional learning. Our training strategy starts with an unconditional GAN and gradually injects the class conditioning into the generator and the objective function. The proposed method for training cGANs with limited data results not only in stable training but also in generating high-quality images, thanks to the early-stage exploitation of the shared information across classes. We analyze the observed mode collapse problem in comprehensive experiments on four datasets. Our approach demonstrates outstanding results compared with state-of-the-art methods and established baselines. The code is available at https://github.com/mshahbazi72/transitional-cGAN