# Structuring Autoencoders

arXiv: https://arxiv.org/abs/1908.02626 · HTML: https://mlsanity.com/paper/1908.02626/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2019.

## Built on by (most cited first, 11 of 11)

- [Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection](https://mlsanity.com/paper/2110.02855/) (2021)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images](https://mlsanity.com/paper/2204.11161/) (2022)
- [MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2211.13968/) (2022)
- [Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2412.17619/) (2024)
- [A Mechanism for Producing Aligned Latent Spaces with Autoencoders](https://mlsanity.com/paper/2106.15456/) (2021)
- [Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework](https://mlsanity.com/paper/2108.12159/) (2021)
- [DAS3D: Dual-modality Anomaly Synthesis for 3D Anomaly Detection](https://mlsanity.com/paper/2410.09821/) (2024)
- [D3A-TS: Denoising-Driven Data Augmentation in Time Series](https://mlsanity.com/paper/2312.05550/) (2023)
- [Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection](https://mlsanity.com/paper/2405.02068/) (2024)
- [Patch-wise Auto-Encoder for Visual Anomaly Detection](https://mlsanity.com/paper/2308.00429/) (2023)

## Abstract (arXiv)

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional Autoencoders have proven to structure data naturally they fail to discover semantic structure that is hard to recognize in the raw data. The SAE solves the problem by enhancing a traditional Autoencoder using weak supervision to form a structured latent space. In the experiments we demonstrate, that the structured latent space allows for a much more efficient data representation for further tasks such as classification for sparsely labeled data, an efficient choice of data to label, and morphing between classes. To demonstrate the general applicability of our method, we show experiments on the benchmark image datasets MNIST, Fashion-MNIST, DeepFashion2 and on a dataset of 3D human shapes.