# Deep Transformation-Invariant Clustering

arXiv: https://arxiv.org/abs/2006.11132 · HTML: https://mlsanity.com/paper/2006.11132/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2020.

## Built on by (most cited first, 26 of 26)

- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [Neural Congealing: Aligning Images to a Joint Semantic Atlas](https://mlsanity.com/paper/2302.03956/) (2023)
- [Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency](https://mlsanity.com/paper/2204.10310/) (2022)
- [Equivariant and Invariant Grounding for Video Question Answering](https://mlsanity.com/paper/2207.12783/) (2022)
- [Self-Interpretable Model with TransformationEquivariant Interpretation](https://mlsanity.com/paper/2111.04927/) (2021)
- [Supervised structure learning](https://mlsanity.com/paper/2311.10300/) (2023)
- [Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach](https://mlsanity.com/paper/2303.12533/) (2023)
- [Representing Shape Collections with Alignment-Aware Linear Models](https://mlsanity.com/paper/2109.01605/) (2021)
- [Unsupervised Image Decomposition with Phase-Correlation Networks](https://mlsanity.com/paper/2110.03473/) (2021)
- [Deep Clustering with a Constraint for Topological Invariance based on Symmetric InfoNCE](https://mlsanity.com/paper/2303.03036/) (2023)
- [Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans](https://mlsanity.com/paper/2304.09704/) (2023)
- [Transformers versus the EM Algorithm in Multi-class Clustering](https://mlsanity.com/paper/2502.06007/) (2025)
- [Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy](https://mlsanity.com/paper/2411.00868/) (2024)
- [The Learnable Typewriter: A Generative Approach to Text Analysis](https://mlsanity.com/paper/2302.01660/) (2023)
- [A Prototype-Oriented Clustering for Domain Shift with Source Privacy](https://mlsanity.com/paper/2302.03807/) (2023)
- [Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent Layers](https://mlsanity.com/paper/2501.01414/) (2025)
- [TextOCVP: Object-Centric Video Prediction with Language Guidance](https://mlsanity.com/paper/2502.11655/) (2025)
- [StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars](https://mlsanity.com/paper/2510.06200/) (2025)
- [FastJAM: a Fast Joint Alignment Model for Images](https://mlsanity.com/paper/2510.22842/) (2025)
- [Fitting large mixture models using stochastic component selection](https://mlsanity.com/paper/2110.04776/) (2021)
- [Unsupervised Difference Learning for Noisy Rigid Image Alignment](https://mlsanity.com/paper/2205.11829/) (2022)
- [Domain Generalization In Robust Invariant Representation](https://mlsanity.com/paper/2304.03431/) (2023)
- [Historical Printed Ornaments: Dataset and Tasks](https://mlsanity.com/paper/2408.08633/) (2024)
- [Deep Sprite-based Image Models: An Analysis](https://mlsanity.com/paper/2604.19480/) (2026)
- [SlotDiT: Object-Centric Representations for Diffusion Transformers](https://mlsanity.com/paper/2609.17414/) (2026)

## Abstract (arXiv)

Recent advances in image clustering typically focus on learning better deep representations. In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and performs clustering directly in image space. This learning process naturally fits in the gradient-based training of K-means and Gaussian mixture model, without requiring any additional loss or hyper-parameters. It leads us to two new deep transformation-invariant clustering frameworks, which jointly learn prototypes and transformations. More specifically, we use deep learning modules that enable us to resolve invariance to spatial, color and morphological transformations. Our approach is conceptually simple and comes with several advantages, including the possibility to easily adapt the desired invariance to the task and a strong interpretability of both cluster centers and assignments to clusters. We demonstrate that our novel approach yields competitive and highly promising results on standard image clustering benchmarks. Finally, we showcase its robustness and the advantages of its improved interpretability by visualizing clustering results over real photograph collections.