# Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

arXiv: https://arxiv.org/abs/1912.02678 · HTML: https://mlsanity.com/paper/1912.02678/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering](https://mlsanity.com/paper/2105.01899/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Contextually Affinitive Neighborhood Refinery for Deep Clustering](https://mlsanity.com/paper/2312.07806/) (2023)
- [Combining pretrained CNN feature extractors to enhance clustering of complex natural images](https://mlsanity.com/paper/2101.02767/) (2021)
- [C3: Cross-instance guided Contrastive Clustering](https://mlsanity.com/paper/2211.07136/) (2022)
- [Dataset Summarization by K Principal Concepts](https://mlsanity.com/paper/2104.03952/) (2021)
- [A Personalized Video-Based Hand Taxonomy: Application for Individuals with Spinal Cord Injury](https://mlsanity.com/paper/2403.18094/) (2024)

## Abstract (arXiv)

The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. The cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task of predicting image rotations. This pushes the network to learn more meaningful image representations that facilitate a better clustering. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on six challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 20% absolute accuracy points, yielding an accuracy of 82% on CIFAR-10, 45% on CIFAR-100 and 69% on STL-10.