paper-with-me

Papers

Bayesian Self-Supervised Contrastive Learning

2023-01-27 · Bin Liu, Bang Wang, Tianrui Li

Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges. As the negative samples are drawn from unlabeled datasets, a randomly selected sample may be actually a false negative to an anchor, leading to incorrect encoder training. This paper proposes a new self-supervised contrastive loss called the BCL loss that still uses random samples from the unlabeled data while correcting the resulting bias with importance weights. The key idea is to design the desired sampling distribution for sampling hard true negative samples under the Bayesian framework. The prominent advantage lies in that the desired sampling distribution is a parametric structure, with a location parameter for debiasing false negative and concentration parameter for mining hard negative, respectively. Experiments validate the effectiveness and superiority of the BCL loss.

📄 PDF Abstract BibTeX arXiv:2301.11673

Code (1)

liubin06/BCL 공식 구현 pytorch

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Incorporating Unlabelled Data into Bayesian Neural Networks

2023-04-04 · Mrinank Sharma, Tom Rainforth, Yee Whye Teh, Vincent Fortuin

Conventional Bayesian Neural Networks (BNNs) are unable to leverage unlabelled data to improve their predictions. To overcome this limitation, we introduce Self-Supervised Bayesian Neural Networks, which use unlabelled d…

Active LearningSelf-Supervised LearningUnsupervised Pre-training

Contrastive Learning for Space-Time Correspondence via Self-Cycle Consistency

2022-01-01 · CVPR 2022 1 · Jeany Son

We propose a novel probabilistic method employing Bayesian Model Averaging and self-cycle regularization for spatio-temporal correspondence learning in videos within a self-supervised learning framework. Most existin…

Contrastive LearningSelf-Supervised Learning

Bayesian Graph Contrastive Learning

2021-12-15 · Arman Hasanzadeh, Mohammadreza Armandpour, Ehsan Hajiramezanali, Mingyuan Zhou 외

Contrastive learning has become a key component of self-supervised learning approaches for graph-structured data. Despite their success, existing graph contrastive learning methods are incapable of uncertainty quantifica…

Contrastive LearningSelf-Supervised LearningUncertainty Quantification

Self-Supervised Learning for 3D Medical Image Analysis using 3D SimCLR and Monte Carlo Dropout

2021-09-29 · Yamen Ali, Aiham Taleb, Marina M. -C. Höhne, Christoph Lippert

Self-supervised learning methods can be used to learn meaningful representations from unlabeled data that can be transferred to supervised downstream tasks to reduce the need for labeled data. In this paper, we propose a…

Brain Tumor SegmentationMedical Image AnalysisMedical Image SegmentationSegmentation+2

Contrastive Bayesian Analysis for Deep Metric Learning

2022-10-10 · Shichao Kan, Zhiquan He, Yigang Cen, Yang Li 외

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive s…

Contrastive LearningMetric Learning