paper-with-me

Papers

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

2023-04-19 · Seongho Joe, Byoungjip Kim, Hoyoung Kang, Kyoungwon Park, Bogun Kim, Jaeseon Park, Joonseok Lee, Youngjune Gwon

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.

📄 PDF Abstract BibTeX arXiv:2304.09369

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningimage-classificationImage ClassificationRepresentation LearningSelf-Supervised LearningUnsupervised Image Classification

Methods 이 논문이 사용한 방법론

DAC 설명 없음

Similar Papers 제목 키워드 기반

Self-supervised object detection from audio-visual correspondence

2021-04-13 · CVPR 2022 1 · Triantafyllos Afouras, Yuki M. Asano, Francois Fagan, Andrea Vedaldi 외

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+1

Clinically Labeled Contrastive Learning for OCT Biomarker Classification

2023-05-24 · Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib 외

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 LearningDiagnostic

Joint Embedding Self-Supervised Learning in the Kernel Regime

2022-09-29 · Bobak T. Kiani, Randall Balestriero, Yubei Chen, Seth Lloyd 외

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 Learning

Clinical Contrastive Learning for Biomarker Detection

2022-11-09 · Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

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 LearningDiagnostic

Masked Contrastive Learning for Anomaly Detection

2021-05-18 · Hyunsoo Cho, Jinseok Seol, Sang-goo Lee

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