ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive Learningimage-classificationImage ClassificationRepresentation LearningSelf-Supervised LearningUnsupervised Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Self-supervised object detection from audio-visual correspondence
We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-…
Objectobject-detectionObject DetectionSound Source Localization+1Clinically Labeled Contrastive Learning for OCT Biomarker Classification
This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety o…
ClassificationContrastive LearningDiagnosticJoint Embedding Self-Supervised Learning in the Kernel Regime
The fundamental goal of self-supervised learning (SSL) is to produce useful representations of data without access to any labels for classifying the data. Modern methods in SSL, which form representations based on known …
Self-Supervised LearningClinical Contrastive Learning for Biomarker Detection
This paper presents a novel positive and negative set selection strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. In the medical field, there exists a variety o…
Contrastive LearningDiagnosticMasked Contrastive Learning for Anomaly Detection
Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demons…
Anomaly DetectionContrastive LearningSelf-Supervised Learning