# Unsupervised Transformation Learning via Convex Relaxations

arXiv: https://arxiv.org/abs/1711.02226 · HTML: https://mlsanity.com/paper/1711.02226/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2017.

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

- [Grounding inductive biases in natural images:invariance stems from variations in data](https://mlsanity.com/paper/2106.05121/) (2021)
- [Toward a Geometrical Understanding of Self-supervised Contrastive Learning](https://mlsanity.com/paper/2205.06926/) (2022)
- [Addressing the Topological Defects of Disentanglement via Distributed Operators](https://mlsanity.com/paper/2102.05623/) (2021)
- [A Generative Model of Symmetry Transformations](https://mlsanity.com/paper/2403.01946/) (2024)
- [Robust Self-Supervised Learning with Lie Groups](https://mlsanity.com/paper/2210.13356/) (2022)

## Abstract (arXiv)

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extrapolate off the training data and can be applied to new types of images.