# Breaking the Reclustering Barrier in Centroid-based Deep Clustering

arXiv: https://arxiv.org/abs/2411.02275 · HTML: https://mlsanity.com/paper/2411.02275/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 70 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Understanding plasticity in neural networks](https://mlsanity.com/paper/2303.01486/) (2023)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [Continual Backprop: Stochastic Gradient Descent with Persistent Randomness](https://mlsanity.com/paper/2108.06325/) (2021)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [Graph Contrastive Clustering](https://mlsanity.com/paper/2104.01429/) (2021)
- [A study on the plasticity of neural networks](https://mlsanity.com/paper/2106.00042/) (2021)
- [Stable Cluster Discrimination for Deep Clustering](https://mlsanity.com/paper/2311.14310/) (2023)
- [The Impact of Reinitialization on Generalization in Convolutional Neural Networks](https://mlsanity.com/paper/2109.00267/) (2021)
- [Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget](https://mlsanity.com/paper/2304.10520/) (2023)
- [When Does Re-initialization Work?](https://mlsanity.com/paper/2206.10011/) (2022)
- [A Survey on Deep Clustering: From the Prior Perspective](https://mlsanity.com/paper/2406.19602/) (2024)
- [Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation](https://mlsanity.com/paper/2303.16521/) (2023)

## Built on by (most cited first, 4 of 4)

- [K*-Means: A Parameter-free Clustering Algorithm](https://mlsanity.com/paper/2505.11904/) (2025)
- [OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction](https://mlsanity.com/paper/2505.13071/) (2025)
- [Clustering High-dimensional Data: Balancing Abstraction and Representation Tutorial at AAAI 2026](https://mlsanity.com/paper/2601.11160/) (2026)
- [Fitting Unknown Number of Hyperplanes with Manifold Optimization](https://mlsanity.com/paper/2605.28501/) (2026)

## Abstract (arXiv)

This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering, which we demonstrate to be insufficient to address performance plateaus. We call this phenomenon the "reclustering barrier" and empirically show when the reclustering barrier occurs, what its underlying mechanisms are, and how it is possible to Break the Reclustering Barrier with our algorithm BRB. BRB avoids early over-commitment to initial clusterings and enables continuous adaptation to reinitialized clustering targets while remaining conceptually simple. Applying our algorithm to widely-used centroid-based DC algorithms, we show that (1) BRB consistently improves performance across a wide range of clustering benchmarks, (2) BRB enables training from scratch, and (3) BRB performs competitively against state-of-the-art DC algorithms when combined with a contrastive loss. We release our code and pre-trained models at https://github.com/Probabilistic-and-Interactive-ML/breaking-the-reclustering-barrier .