# Latent space configuration for improved generalization in supervised autoencoder neural networks

arXiv: https://arxiv.org/abs/2402.08441 · HTML: https://mlsanity.com/paper/2402.08441/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing](https://mlsanity.com/paper/1703.05446/) (2017)
- [Pooling Methods in Deep Neural Networks, a Review](https://mlsanity.com/paper/2009.07485/) (2020)
- [Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections](https://mlsanity.com/paper/1606.08921/) (2016)
- [Anomaly Detection with Adversarial Dual Autoencoders](https://mlsanity.com/paper/1902.06924/) (2019)
- [PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks](https://mlsanity.com/paper/2006.07827/) (2020)
- [A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids](https://mlsanity.com/paper/1902.00220/) (2019)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)

## Built on by (most cited first, 6 of 6)

- [Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes](https://mlsanity.com/paper/2510.04090/) (2025)
- [Series of quasi-uniform scatterings with fast search, root systems and neural network classifications](https://mlsanity.com/paper/2512.04865/) (2025)
- [Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces](https://mlsanity.com/paper/2512.07509/) (2025)
- [Improving analytical color and texture similarity estimation methods for dataset-agnostic person reidentification](https://mlsanity.com/paper/2412.05076/) (2024)
- [Deep Learning Approaches for Blood Disease Diagnosis Across Hematopoietic Lineages](https://mlsanity.com/paper/2503.20049/) (2025)
- [Using predefined vector systems to speed up neural network multimillion class classification](https://mlsanity.com/paper/2604.00779/) (2026)

## Abstract (arXiv)

Autoencoders (AE) are simple yet powerful class of neural networks that compress data by projecting input into low-dimensional latent space (LS). Whereas LS is formed according to the loss function minimization during training, its properties and topology are not controlled directly. In this paper we focus on AE LS properties and propose two methods for obtaining LS with desired topology, called LS configuration. The proposed methods include loss configuration using a geometric loss term that acts directly in LS, and encoder configuration. We show that the former allows to reliably obtain LS with desired configuration by defining the positions and shapes of LS clusters for supervised AE (SAE). Knowing LS configuration allows to define similarity measure in LS to predict labels or estimate similarity for multiple inputs without using decoders or classifiers. We also show that this leads to more stable and interpretable training. We show that SAE trained for clothes texture classification using the proposed method generalizes well to unseen data from LIP, Market1501, and WildTrack datasets without fine-tuning, and even allows to evaluate similarity for unseen classes. We further illustrate the advantages of pre-configured LS similarity estimation with cross-dataset searches and text-based search using a text query without language models.