# SCAN: Learning to Classify Images without Labels

arXiv: https://arxiv.org/abs/2005.12320 · HTML: https://mlsanity.com/paper/2005.12320/

## Key facts

- Cited by 352 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 30 of 352)

- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Efficient Training of Visual Transformers with Small Datasets](https://mlsanity.com/paper/2106.03746/) (2021)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/2111.10265/) (2021)
- [Self-Supervised Learning of Object Parts for Semantic Segmentation](https://mlsanity.com/paper/2204.13101/) (2022)
- [Adversarial Masking for Self-Supervised Learning](https://mlsanity.com/paper/2201.13100/) (2022)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Wavelet Convolutions for Large Receptive Fields](https://mlsanity.com/paper/2407.05848/) (2024)
- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes](https://mlsanity.com/paper/2209.08776/) (2022)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning](https://mlsanity.com/paper/2102.10680/) (2021)
- [Active Learning Through a Covering Lens](https://mlsanity.com/paper/2205.11320/) (2022)
- [Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation](https://mlsanity.com/paper/2106.00131/) (2021)
- [Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos](https://mlsanity.com/paper/2104.12671/) (2021)
- [Graph Contrastive Clustering](https://mlsanity.com/paper/2104.01429/) (2021)
- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)

## Abstract (arXiv)

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CIFAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any ground-truth annotations. The code is made publicly available at https://github.com/wvangansbeke/Unsupervised-Classification.