# A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids

arXiv: https://arxiv.org/abs/1902.00220 · HTML: https://mlsanity.com/paper/1902.00220/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2019.

## Built on by (most cited first, 8 of 8)

- [Latent space configuration for improved generalization in supervised autoencoder neural networks](https://mlsanity.com/paper/2402.08441/) (2024)
- [Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.18104/) (2023)
- [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)
- [A Softmax-free Loss Function Based on Predefined Optimal-distribution of Latent Features for Deep Learning Classifier](https://mlsanity.com/paper/2111.15449/) (2021)
- [Semi-supervised classification using a supervised autoencoder for biomedical applications](https://mlsanity.com/paper/2208.10315/) (2022)
- [Out-of-distribution detection based on subspace projection of high-dimensional features output by the last convolutional layer](https://mlsanity.com/paper/2405.01662/) (2024)
- [Extractive text summarisation of Privacy Policy documents using machine learning approaches](https://mlsanity.com/paper/2404.08686/) (2024)

## Abstract (arXiv)

Classic variational autoencoders are used to learn complex data distributions, that are built on standard function approximators. Especially, VAE has shown promise on a lot of complex task. In this paper, a new autoencoder model - classification supervised autoencoder (CSAE) based on predefined evenly-distributed class centroids (PEDCC) is proposed. Our method uses PEDCC of latent variables to train the network to ensure the maximization of inter-class distance and the minimization of inner-class distance. Instead of learning mean/variance of latent variables distribution and taking reparameterization of VAE, latent variables of CSAE are directly used to classify and as input of decoder. In addition, a new loss function is proposed to combine the loss function of classification. Based on the basic structure of the universal autoencoder, we realized the comprehensive optimal results of encoding, decoding, classification, and good model generalization performance at the same time. Theoretical advantages are reflected in experimental results.