# Convolutional Clustering for Unsupervised Learning

arXiv: https://arxiv.org/abs/1511.06241 · HTML: https://mlsanity.com/paper/1511.06241/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

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

- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Hebbian Deep Learning Without Feedback](https://mlsanity.com/paper/2209.11883/) (2022)
- [Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16236/) (2023)
- [CHALLENGER: Training with Attribution Maps](https://mlsanity.com/paper/2205.15094/) (2022)
- [ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification](https://mlsanity.com/paper/2304.00219/) (2023)
- [Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representations](https://mlsanity.com/paper/2312.00101/) (2023)
- [Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors](https://mlsanity.com/paper/2401.17400/) (2024)

## Abstract (arXiv)

The task of labeling data for training deep neural networks is daunting and tedious, requiring millions of labels to achieve the current state-of-the-art results. Such reliance on large amounts of labeled data can be relaxed by exploiting hierarchical features via unsupervised learning techniques. In this work, we propose to train a deep convolutional network based on an enhanced version of the k-means clustering algorithm, which reduces the number of correlated parameters in the form of similar filters, and thus increases test categorization accuracy. We call our algorithm convolutional k-means clustering. We further show that learning the connection between the layers of a deep convolutional neural network improves its ability to be trained on a smaller amount of labeled data. Our experiments show that the proposed algorithm outperforms other techniques that learn filters unsupervised. Specifically, we obtained a test accuracy of 74.1% on STL-10 and a test error of 0.5% on MNIST.