SCAN: Learning to Classify Images without Labels
| Autor: | Stamatios Georgoulis, Wouter Van Gansbeke, Simon Vandenhende, Luc Van Gool, Marc Proesmans |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Self supervised learning Contextual image classification business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition Task (project management) Machine Learning (cs.LG) Code (cryptography) Unsupervised learning Learning methods Artificial intelligence Cluster analysis business Feature learning |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030586065 ECCV (10) |
| DOI: | 10.48550/arxiv.2005.12320 |
| Popis: | 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. Comment: Accepted at ECCV 2020. Includes supplementary. Code and pretrained models at https://github.com/wvangansbeke/Unsupervised-Classification |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|