# CNN features are also great at unsupervised classification

arXiv: https://arxiv.org/abs/1707.01700 · HTML: https://mlsanity.com/paper/1707.01700/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2017.

## Built on by (most cited first, 9 of 9)

- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Combining pretrained CNN feature extractors to enhance clustering of complex natural images](https://mlsanity.com/paper/2101.02767/) (2021)
- [What Image Features Boost Housing Market Predictions?](https://mlsanity.com/paper/2107.07148/) (2021)
- [Contrastive Hierarchical Clustering](https://mlsanity.com/paper/2303.03389/) (2023)
- [Dataset and Case Studies for Visual Near-Duplicates Detection in the Context of Social Media](https://mlsanity.com/paper/2203.07167/) (2022)
- [Iterative Cluster Harvesting for Wafer Map Defect Patterns](https://mlsanity.com/paper/2404.15436/) (2024)
- [An Image is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings](https://mlsanity.com/paper/2504.10004/) (2025)
- [Artificial Perceptual Learning: Image Categorization with Weak Supervision](https://mlsanity.com/paper/2106.07559/) (2021)
- [A Personalized Video-Based Hand Taxonomy: Application for Individuals with Spinal Cord Injury](https://mlsanity.com/paper/2403.18094/) (2024)

## Abstract (arXiv)

This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems. We study the impact of different pretrained CNN feature extractors on the problem of image set clustering for object classification as well as fine-grained classification. We propose a rather straightforward pipeline combining deep-feature extraction using a CNN pretrained on ImageNet and a classic clustering algorithm to classify sets of images. This approach is compared to state-of-the-art algorithms in image-clustering and provides better results. These results strengthen the belief that supervised training of deep CNN on large datasets, with a large variability of classes, extracts better features than most carefully designed engineering approaches, even for unsupervised tasks. We also validate our approach on a robotic application, consisting in sorting and storing objects smartly based on clustering.