# Early Stopping Criteria for Training Generative Adversarial Networks in Biomedical Imaging

arXiv: https://arxiv.org/abs/2405.20987 · HTML: https://mlsanity.com/paper/2405.20987/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 18 of 18)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Improved Consistency Regularization for GANs](https://mlsanity.com/paper/2002.04724/) (2020)
- [Anycost GANs for Interactive Image Synthesis and Editing](https://mlsanity.com/paper/2103.03243/) (2021)
- [Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluation](https://mlsanity.com/paper/2012.03769/) (2020)
- [Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs](https://mlsanity.com/paper/2010.03975/) (2020)
- [A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing](https://mlsanity.com/paper/2110.01442/) (2021)
- [Generalization Error of GAN from the Discriminator's Perspective](https://mlsanity.com/paper/2107.03633/) (2021)
- [Addressing the Intra-class Mode Collapse Problem using Adaptive Input Image Normalization in GAN-based X-ray Images](https://mlsanity.com/paper/2201.10324/) (2022)
- [Stop Throwing Away Discriminators! Re-using Adversaries for Test-Time Training](https://mlsanity.com/paper/2108.12280/) (2021)
- [A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis](https://mlsanity.com/paper/2210.06334/) (2022)
- [Assessing Intra-class Diversity and Quality of Synthetically Generated Images in a Biomedical and Non-biomedical Setting](https://mlsanity.com/paper/2308.02505/) (2023)
- [Overcoming challenges in leveraging GANs for few-shot data augmentation](https://mlsanity.com/paper/2203.16662/) (2022)

## Built on by (most cited first, 1 of 1)

- [Trustworthy image-to-image translation: evaluating uncertainty calibration in unpaired training scenarios](https://mlsanity.com/paper/2501.17570/) (2025)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have high computational costs to train their complex architectures. Throughout the training process, GANs' output is analyzed qualitatively based on the loss and synthetic images' diversity and quality. Based on this qualitative analysis, training is manually halted once the desired synthetic images are generated. By utilizing an early stopping criterion, the computational cost and dependence on manual oversight can be reduced yet impacted by training problems such as mode collapse, non-convergence, and instability. This is particularly prevalent in biomedical imagery, where training problems degrade the diversity and quality of synthetic images, and the high computational cost associated with training makes complex architectures increasingly inaccessible. This work proposes a novel early stopping criteria to quantitatively detect training problems, halt training, and reduce the computational costs associated with synthesizing biomedical images. Firstly, the range of generator and discriminator loss values is investigated to assess whether mode collapse, non-convergence, and instability occur sequentially, concurrently, or interchangeably throughout the training of GANs. Secondly, utilizing these occurrences in conjunction with the Mean Structural Similarity Index (MS-SSIM) and Fr'echet Inception Distance (FID) scores of synthetic images forms the basis of the proposed early stopping criteria. This work helps identify the occurrence of training problems in GANs using low-resource computational cost and reduces training time to generate diversified and high-quality synthetic images.