# Progressive Cluster Purification for Unsupervised Feature Learning

arXiv: https://arxiv.org/abs/2007.02577 · HTML: https://mlsanity.com/paper/2007.02577/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

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

- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Dense Semantic Contrast for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2109.07756/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition](https://mlsanity.com/paper/2503.18746/) (2025)
- [MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification](https://mlsanity.com/paper/2107.00808/) (2021)
- [Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images](https://mlsanity.com/paper/2109.03451/) (2021)
- [Self-supervised Feature-Gate Coupling for Dynamic Network Pruning](https://mlsanity.com/paper/2111.14302/) (2021)
- [Masked Next-Scale Prediction for Self-supervised Scene Text Recognition](https://mlsanity.com/paper/2605.14885/) (2026)

## Abstract (arXiv)

In unsupervised feature learning, sample specificity based methods ignore the inter-class information, which deteriorates the discriminative capability of representation models. Clustering based methods are error-prone to explore the complete class boundary information due to the inevitable class inconsistent samples in each cluster. In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner. Our approach, referred to as Progressive Cluster Purification (PCP), implements progressive clustering by gradually reducing the number of clusters during training, while the sizes of clusters continuously expand consistently with the growth of model representation capability. With a well-designed cluster purification mechanism, it further purifies clusters by filtering noise samples which facilitate the subsequent feature learning by utilizing the refined clusters as pseudo-labels. Experiments on commonly used benchmarks demonstrate that the proposed PCP improves baseline method with significant margins. Our code will be available at https://github.com/zhangyifei0115/PCP.