paper-with-me

홈 › Papers

Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound

2024-03-12 · Blake VanBerlo, Alexander Wong, Jesse Hoey, Robert Arntfield

Self-supervised learning (SSL) is one strategy for addressing the paucity of labelled data in medical imaging by learning representations from unlabelled images. Contrastive and non-contrastive SSL methods produce learned representations that are similar for pairs of related images. Such pairs are commonly constructed by randomly distorting the same image twice. The videographic nature of ultrasound offers flexibility for defining the similarity relationship between pairs of images. In this study, we investigated the effect of utilizing proximal, distinct images from the same B-mode ultrasound video as pairs for SSL. Additionally, we introduced a sample weighting scheme that increases the weight of closer image pairs and demonstrated how it can be integrated into SSL objectives. Named Intra-Video Positive Pairs (IVPP), the method surpassed previous ultrasound-specific contrastive learning methods' average test accuracy on COVID-19 classification with the POCUS dataset by $\ge 1.3\%$. Detailed investigations of IVPP's hyperparameters revealed that some combinations of IVPP hyperparameters can lead to improved or worsened performance, depending on the downstream task. Guidelines for practitioners were synthesized based on the results, such as the merit of IVPP with task-specific hyperparameters, and the improved performance of contrastive methods for ultrasound compared to non-contrastive counterparts.

📄 PDF Abstract BibTeX arXiv:2403.07715

Code (1)

bvanberl/ivpp 공식 구현 pytorch

Tasks

Contrastive LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Nearest-Neighbor Inter-Intra Contrastive Learning from Unlabeled Videos

2023-03-13 · David Fan, Deyu Yang, Xinyu Li, Vimal Bhat 외

Contrastive learning has recently narrowed the gap between self-supervised and supervised methods in image and video domain. State-of-the-art video contrastive learning methods such as CVRL and $\rho$-MoCo spatiotemporal…

Contrastive LearningDiversity

Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework

2020-08-06 · Li Tao, Xueting Wang, Toshihiko Yamasaki

We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. …

Action Recognition In VideosContrastive LearningRepresentation LearningRetrieval+4

SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos

2022-06-25 · CVPR 2022 1 · Salar Hosseini Khorasgani, Yuxuan Chen, Florian Shkurti

Self-supervised methods have significantly closed the gap with end-to-end supervised learning for image classification. In the case of human action videos, however, where both appearance and motion are significant factor…

Action ClassificationClusteringContrastive Learningimage-classification+5

Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency

2021-05-13 · ICCV 2021 10 · Haiping Wu, Xiaolong Wang

Recent works have advanced the performance of self-supervised representation learning by a large margin. The core among these methods is intra-image invariance learning. Two different transformations of one image instanc…

Action RecognitionContrastive Learningimage-classificationImage Classification+4

Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning

2024-08-09 · Yunhui Liu, Huaisong Zhang, Tieke He, Tao Zheng 외

Contrastive learning is a significant paradigm in graph self-supervised learning. However, it requires negative samples to prevent model collapse and learn discriminative representations. These negative samples inevitabl…

Contrastive LearningNode ClassificationNode ClusteringRepresentation Learning+1