# Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation

arXiv: https://arxiv.org/abs/2303.16521 · HTML: https://mlsanity.com/paper/2303.16521/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction](https://mlsanity.com/paper/1611.09842/) (2016)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Online Deep Clustering for Unsupervised Representation Learning](https://mlsanity.com/paper/2006.10645/) (2020)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering](https://mlsanity.com/paper/2002.11863/) (2020)
- [Deep Robust Clustering by Contrastive Learning](https://mlsanity.com/paper/2008.03030/) (2020)
- [An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clustering](https://mlsanity.com/paper/1302.1552/) (2013)
- [Deep clustering with concrete k-means](https://mlsanity.com/paper/1910.08031/) (2019)
- [Deep Clustering by Semantic Contrastive Learning](https://mlsanity.com/paper/2103.02662/) (2021)
- [Selective Pseudo-label Clustering](https://mlsanity.com/paper/2107.10692/) (2021)
- [Representation Learning for Clustering via Building Consensus](https://mlsanity.com/paper/2105.01289/) (2021)
- [Large-Scale Hyperspectral Image Clustering Using Contrastive Learning](https://mlsanity.com/paper/2111.07945/) (2021)
- [A Comparative study Between Fuzzy Clustering Algorithm and Hard Clustering Algorithm](https://mlsanity.com/paper/1404.6059/) (2014)
- [Efficient Deep Clustering of Human Activities and How to Improve Evaluation](https://mlsanity.com/paper/2209.08335/) (2022)

## Built on by (most cited first, 7 of 7)

- [A Modular Approach for Multimodal Summarization of TV Shows](https://mlsanity.com/paper/2403.03823/) (2024)
- [ScreenWriter: Automatic Screenplay Generation and Movie Summarisation](https://mlsanity.com/paper/2410.19809/) (2024)
- [Breaking the Reclustering Barrier in Centroid-based Deep Clustering](https://mlsanity.com/paper/2411.02275/) (2024)
- [Parameter-free Video Segmentation for Vision and Language Understanding](https://mlsanity.com/paper/2503.01201/) (2025)
- [K*-Means: A Parameter-free Clustering Algorithm](https://mlsanity.com/paper/2505.11904/) (2025)
- [Towards a Universal Method for Meaningful Signal Detection](https://mlsanity.com/paper/2408.00016/) (2024)
- [MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding](https://mlsanity.com/paper/2508.02480/) (2025)

## Abstract (arXiv)

Online deep clustering refers to the joint use of a feature extraction network and a clustering model to assign cluster labels to each new data point or batch as it is processed. While faster and more versatile than offline methods, online clustering can easily reach the collapsed solution where the encoder maps all inputs to the same point and all are put into a single cluster. Successful existing models have employed various techniques to avoid this problem, most of which require data augmentation or which aim to make the average soft assignment across the dataset the same for each cluster. We propose a method that does not require data augmentation, and that, differently from existing methods, regularizes the hard assignments. Using a Bayesian framework, we derive an intuitive optimization objective that can be straightforwardly included in the training of the encoder network. Tested on four image datasets and one human-activity recognition dataset, it consistently avoids collapse more robustly than other methods and leads to more accurate clustering. We also conduct further experiments and analyses justifying our choice to regularize the hard cluster assignments. Code is available at https://github.com/Lou1sM/online_hard_clustering.