# Improving Image Clustering With Multiple Pretrained CNN Feature Extractors

arXiv: https://arxiv.org/abs/1807.07760 · HTML: https://mlsanity.com/paper/1807.07760/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering](https://mlsanity.com/paper/2404.15655/) (2024)
- [AugDMC: Data Augmentation Guided Deep Multiple Clustering](https://mlsanity.com/paper/2306.13023/) (2023)
- [Combining pretrained CNN feature extractors to enhance clustering of complex natural images](https://mlsanity.com/paper/2101.02767/) (2021)
- [Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift](https://mlsanity.com/paper/2103.14417/) (2021)
- [Dual-disentangled Deep Multiple Clustering](https://mlsanity.com/paper/2402.05310/) (2024)
- [Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs](https://mlsanity.com/paper/2503.22241/) (2025)
- [ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering](https://mlsanity.com/paper/2512.00725/) (2025)
- [Geometric Digital Twinning of Industrial Facilities: Retrieval of Industrial Shapes](https://mlsanity.com/paper/2202.04834/) (2022)
- [CNN-based Classification Framework for Lung Tissues with Auxiliary Information](https://mlsanity.com/paper/2206.06701/) (2022)
- [In-Context Clustering with Large Language Models](https://mlsanity.com/paper/2510.08466/) (2025)
- [Multi-modal Dynamic Proxy Learning for Personalized Multiple Clustering](https://mlsanity.com/paper/2511.07274/) (2025)
- [Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent](https://mlsanity.com/paper/2606.24094/) (2026)

## Abstract (arXiv)

For many image clustering problems, replacing raw image data with features extracted by a pretrained convolutional neural network (CNN), leads to better clustering performance. However, the specific features extracted, and, by extension, the selected CNN architecture, can have a major impact on the clustering results. In practice, this crucial design choice is often decided arbitrarily due to the impossibility of using cross-validation with unsupervised learning problems. However, information contained in the different pretrained CNN architectures may be complementary, even when pretrained on the same data. To improve clustering performance, we rephrase the image clustering problem as a multi-view clustering (MVC) problem that considers multiple different pretrained feature extractors as different "views" of the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. Our experimental results, conducted on three different natural image datasets, show that: 1. using multiple pretrained CNNs jointly as feature extractors improves image clustering; 2. using an end-to-end approach improves MVC; and 3. combining both produces state-of-the-art results for the problem of image clustering.