# Selective Pseudo-label Clustering

arXiv: https://arxiv.org/abs/2107.10692 · HTML: https://mlsanity.com/paper/2107.10692/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 22 Jul 2021.

## Builds on (most cited first, 22 of 22)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering](https://mlsanity.com/paper/1610.04794/) (2016)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization](https://mlsanity.com/paper/1704.06327/) (2017)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [ClusterGAN : Latent Space Clustering in Generative Adversarial Networks](https://mlsanity.com/paper/1809.03627/) (2018)
- [Loss Functions for Neural Networks for Image Processing](https://mlsanity.com/paper/1511.08861/) (2015)
- [Deep Multimodal Subspace Clustering Networks](https://mlsanity.com/paper/1804.06498/) (2018)
- [N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding](https://mlsanity.com/paper/1908.05968/) (2019)
- [Deep Density-based Image Clustering](https://mlsanity.com/paper/1812.04287/) (2018)
- [Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction](https://mlsanity.com/paper/1901.07752/) (2019)
- [Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift](https://mlsanity.com/paper/1909.11832/) (2019)
- [Deep clustering with concrete k-means](https://mlsanity.com/paper/1910.08031/) (2019)
- [Double cycle-consistent generative adversarial network for unsupervised conditional generation](https://mlsanity.com/paper/1911.05210/) (2019)
- [GAN-EM: GAN based EM learning framework](https://mlsanity.com/paper/1812.00335/) (2018)

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

- [Semantic-Enhanced Image Clustering](https://mlsanity.com/paper/2208.09849/) (2022)
- [ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining](https://mlsanity.com/paper/2312.09249/) (2023)
- [A Modular Approach for Multimodal Summarization of TV Shows](https://mlsanity.com/paper/2403.03823/) (2024)
- [A Simple Approach to Automated Spectral Clustering](https://mlsanity.com/paper/2107.12183/) (2021)
- [Minimum Description Length Clustering to Measure Meaningful Image Complexity](https://mlsanity.com/paper/2306.14937/) (2023)
- [Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation](https://mlsanity.com/paper/2303.16521/) (2023)
- [Efficient Deep Clustering of Human Activities and How to Improve Evaluation](https://mlsanity.com/paper/2209.08335/) (2022)
- [K*-Means: A Parameter-free Clustering Algorithm](https://mlsanity.com/paper/2505.11904/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering techniques. As clustering is typically performed in a purely unsupervised setting, where no training labels are available, the question then arises as to how the DNN feature extractor can be trained. The most accurate existing approaches combine the training of the DNN with the clustering objective, so that information from the clustering process can be used to update the DNN to produce better features for clustering. One problem with this approach is that these ``pseudo-labels'' produced by the clustering algorithm are noisy, and any errors that they contain will hurt the training of the DNN. In this paper, we propose selective pseudo-label clustering, which uses only the most confident pseudo-labels for training the~DNN. We formally prove the performance gains under certain conditions. Applied to the task of image clustering, the new approach achieves a state-of-the-art performance on three popular image datasets. Code is available at https://github.com/Lou1sM/clustering.