# Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis

arXiv: https://arxiv.org/abs/1811.00473 · HTML: https://mlsanity.com/paper/1811.00473/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

## Built on by (most cited first, 5 of 5)

- [LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood](https://mlsanity.com/paper/2206.14882/) (2022)
- [Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning](https://mlsanity.com/paper/2103.01895/) (2021)
- [Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond](https://mlsanity.com/paper/2109.02752/) (2021)
- [Unsupervised End-to-End Training with a Self-Defined Target](https://mlsanity.com/paper/2403.12116/) (2024)
- [G2L: A Geometric Approach for Generating Pseudo-labels that Improve Transfer Learning](https://mlsanity.com/paper/2207.03554/) (2022)

## Abstract (arXiv)

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investigate different auto-encoder (AE) architectures, which require no labels, and explore training strategies to learn representations from images. The models are evaluated considering both the reconstruction error of the images and the feature spaces in terms of their discriminative power. We study the role of dense and convolutional layers on the results, as well as the depth and capacity of the networks, since those are shown to affect both the dimensionality reduction and the capability of generalising for different visual domains. Classification results with AE features were as discriminative as pre-trained CNN features. Our findings can be used as guidelines for the design of unsupervised representation learning methods within and across domains.