# An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

arXiv: https://arxiv.org/abs/1906.03905 · HTML: https://mlsanity.com/paper/1906.03905/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [Deep Temporal Contrastive Clustering](https://mlsanity.com/paper/2212.14366/) (2022)
- [Generation and frame characteristics of predefined evenly-distributed class centroids for pattern classification](https://mlsanity.com/paper/2105.00401/) (2021)
- [Effective Out-of-Distribution Detection in Classifier Based on PEDCC-Loss](https://mlsanity.com/paper/2204.04665/) (2022)
- [Heterogeneous Tri-stream Clustering Network](https://mlsanity.com/paper/2301.04451/) (2023)
- [How to boost autoencoders?](https://mlsanity.com/paper/2110.15307/) (2021)
- [Image Clustering Algorithm Based on Self-Supervised Pretrained Models and Latent Feature Distribution Optimization](https://mlsanity.com/paper/2408.01920/) (2024)
- [On filter design in deep convolutional neural network](https://mlsanity.com/paper/2410.21644/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance. Specifically, we perform one-to-one data augmentation to learn the more effective features. The data and the augmented data are simultaneously input into the autoencoder to obtain latent features and the augmented latent features whose similarity are constrained by an augmentation loss. Then, making use of the maximum mean discrepancy distance (MMD), we combine the latent features and augmented latent features to make their distribution close to the PEDCC distribution (uniform distribution between classes, Dirac distribution within the class) to further learn clustering-oriented features. At the same time, the MSE of the original input image and reconstructed image is used as reconstruction constraint, and the Sobel smooth loss to build generalization constraint to improve the generalization ability. Finally, extensive experiments on three common datasets MNIST, Fashion-MNIST, COIL20 are conducted. The experimental results show that the algorithm has achieved the best clustering results so far. In addition, we can use the predefined PEDCC class centers, and the decoder to clearly generate the samples of each class. The code can be downloaded at https://github.com/zyWang-Power/Clustering!