# Consensus Clustering With Unsupervised Representation Learning

arXiv: https://arxiv.org/abs/2010.01245 · HTML: https://mlsanity.com/paper/2010.01245/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization](https://mlsanity.com/paper/2108.02183/) (2021)
- [Static and Dynamic Concepts for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2207.12795/) (2022)
- [DivClust: Controlling Diversity in Deep Clustering](https://mlsanity.com/paper/2304.01042/) (2023)
- [Self-supervised Hypergraphs for Learning Multiple World Interpretations](https://mlsanity.com/paper/2308.07615/) (2023)
- [Representation Learning for Clustering via Building Consensus](https://mlsanity.com/paper/2105.01289/) (2021)
- [Deep Clustering With Consensus Representations](https://mlsanity.com/paper/2210.07063/) (2022)
- [Aircraft Trajectory Segmentation-based Contrastive Coding: A Framework for Self-supervised Trajectory Representation](https://mlsanity.com/paper/2407.20028/) (2024)
- [GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2207.10158/) (2022)
- [ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision](https://mlsanity.com/paper/2304.09369/) (2023)
- [Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering](https://mlsanity.com/paper/2310.17869/) (2023)

## Abstract (arXiv)

Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or have a similar cluster assignment. Bootstrap Your Own Latent (BYOL) is one such representation learning algorithm that has achieved state-of-the-art results in self-supervised image classification on ImageNet under the linear evaluation protocol. However, the utility of the learnt features of BYOL to perform clustering is not explored. In this work, we study the clustering ability of BYOL and observe that features learnt using BYOL may not be optimal for clustering. We propose a novel consensus clustering based loss function, and train BYOL with the proposed loss in an end-to-end way that improves the clustering ability and outperforms similar clustering based methods on some popular computer vision datasets.