# Label-Removed Generative Adversarial Networks Incorporating with K-Means

arXiv: https://arxiv.org/abs/1902.06938 · HTML: https://mlsanity.com/paper/1902.06938/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2019.

## Built on by (most cited first, 2 of 2)

- [Active CT Reconstruction with a Learned Sampling Policy](https://mlsanity.com/paper/2211.01670/) (2022)
- [Weakly-Supervised Anomaly Detection in Surveillance Videos Based on Two-Stream I3D Convolution Network](https://mlsanity.com/paper/2411.08755/) (2024)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have achieved great success in generating realistic images. Most of these are conditional models, although acquisition of class labels is expensive and time-consuming in practice. To reduce the dependence on labeled data, we propose an un-conditional generative adversarial model, called K-Means-GAN (KM-GAN), which incorporates the idea of updating centers in K-Means into GANs. Specifically, we redesign the framework of GANs by applying K-Means on the features extracted from the discriminator. With obtained labels from K-Means, we propose new objective functions from the perspective of deep metric learning (DML). Distinct from previous works, the discriminator is treated as a feature extractor rather than a classifier in KM-GAN, meanwhile utilization of K-Means makes features of the discriminator more representative. Experiments are conducted on various datasets, such as MNIST, Fashion-10, CIFAR-10 and CelebA, and show that the quality of samples generated by KM-GAN is comparable to some conditional generative adversarial models.