# Transform Invariant Auto-encoder

arXiv: https://arxiv.org/abs/1709.03754 · HTML: https://mlsanity.com/paper/1709.03754/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

## Built on by (most cited first, 4 of 4)

- [AICCA: AI-driven Cloud Classification Atlas](https://mlsanity.com/paper/2209.15096/) (2022)
- [Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder](https://mlsanity.com/paper/2103.04885/) (2021)
- [Insight into cloud processes from unsupervised classification with a rotationally invariant autoencoder](https://mlsanity.com/paper/2211.00860/) (2022)
- [Robust Spectral Anomaly Detection in EELS Spectral Images via Three Dimensional Convolutional Variational Autoencoders](https://mlsanity.com/paper/2412.16200/) (2024)

## Abstract (arXiv)

The auto-encoder method is a type of dimensionality reduction method. A mapping from a vector to a descriptor that represents essential information can be automatically generated from a set of vectors without any supervising information. However, an image and its spatially shifted version are encoded into different descriptors by an existing ordinary auto-encoder because each descriptor includes a spatial subpattern and its position. To generate a descriptor representing a spatial subpattern in an image, we need to normalize its spatial position in the images prior to training an ordinary auto-encoder; however, such a normalization is generally difficult for images without obvious standard positions. We propose a transform invariant auto-encoder and an inference model of transform parameters. By the proposed method, we can separate an input into a transform invariant descriptor and transform parameters. The proposed method can be applied to various auto-encoders without requiring any special modules or labeled training samples. By applying it to shift transforms, we can achieve a shift invariant auto-encoder that can extract a typical spatial subpattern independent of its relative position in a window. In addition, we can achieve a model that can infer shift parameters required to restore the input from the typical subpattern. As an example of the proposed method, we demonstrate that a descriptor generated by a shift invariant auto-encoder can represent a typical spatial subpattern. In addition, we demonstrate the imitation of a human hand by a robot hand as an example of a regression based on spatial subpatterns.