# Spatial Transformer K-Means

arXiv: https://arxiv.org/abs/2202.07829 · HTML: https://mlsanity.com/paper/2202.07829/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 70 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [An Unsupervised Learning Model for Deformable Medical Image Registration](https://mlsanity.com/paper/1802.02604/) (2018)
- [AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark](https://mlsanity.com/paper/1807.03418/) (2018)
- [Learning Conditional Deformable Templates with Convolutional Networks](https://mlsanity.com/paper/1908.02738/) (2019)
- [The Geometry of Deep Networks: Power Diagram Subdivision](https://mlsanity.com/paper/1905.08443/) (2019)
- [Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping](https://mlsanity.com/paper/1906.05947/) (2019)
- [On the Complexity of Randomly Weighted Voronoi Diagrams](https://mlsanity.com/paper/1401.1477/) (2014)
- [SymJAX: symbolic CPU/GPU/TPU programming](https://mlsanity.com/paper/2005.10635/) (2020)

## Built on by (most cited first, 2 of 2)

- [Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?](https://mlsanity.com/paper/2406.10743/) (2024)
- [Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head](https://mlsanity.com/paper/2302.10260/) (2023)

## Abstract (arXiv)

K-means defines one of the most employed centroid-based clustering algorithms with performances tied to the data's embedding. Intricate data embeddings have been designed to push K-means performances at the cost of reduced theoretical guarantees and interpretability of the results. Instead, we propose preserving the intrinsic data space and augment K-means with a similarity measure invariant to non-rigid transformations. This enables (i) the reduction of intrinsic nuisances associated with the data, reducing the complexity of the clustering task and increasing performances and producing state-of-the-art results, (ii) clustering in the input space of the data, leading to a fully interpretable clustering algorithm, and (iii) the benefit of convergence guarantees.