ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision

• Main Authors: Joe, Seongho, Kim, Byoungjip, Kang, Hoyoung, Park, Kyoungwon, Kim, Bogun, Park, Jaeseon, Lee, Joonseok, Gwon, Youngjune
• Format: Journal Article
• Language: English
• Published: 19-04-2023
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning
• DOI: 10.48550/arxiv.2304.09369

2022 26th International Conference on Pattern Recognition (ICPR),
Montreal, QC, Canada, 2022, pp. 4685-4692 The recent advances in representation learning inspire us to take on the
challenging problem of unsupervised image classification tasks in a principled
way. We propose ContraCluster, an unsupervised image classification method that
combines clustering with the power of contrastive self-supervised learning.
ContraCluster consists of three stages: (1) contrastive self-supervised
pre-training (CPT), (2) contrastive prototype sampling (CPS), and (3)
prototype-based semi-supervised fine-tuning (PB-SFT). CPS can select highly
accurate, categorically prototypical images in an embedding space learned by
contrastive learning. We use sampled prototypes as noisy labeled data to
perform semi-supervised fine-tuning (PB-SFT), leveraging small prototypes and
large unlabeled data to further enhance the accuracy. We demonstrate
empirically that ContraCluster achieves new state-of-the-art results for
standard benchmark datasets including CIFAR-10, STL-10, and ImageNet-10. For
example, ContraCluster achieves about 90.8% accuracy for CIFAR-10, which
outperforms DAC (52.2%), IIC (61.7%), and SCAN (87.6%) by a large margin.
Without any labels, ContraCluster can achieve a 90.8% accuracy that is
comparable to 95.8% by the best supervised counterpart.