Saved in:
Bibliographic Details
Main Authors: Reasat, Tahsin, Sushmit, Asif, Smith, David S.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.16247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914878079369216
author Reasat, Tahsin
Sushmit, Asif
Smith, David S.
author_facet Reasat, Tahsin
Sushmit, Asif
Smith, David S.
contents Deep learning (DL) based diagnostics systems can provide accurate and robust quantitative analysis in digital pathology. These algorithms require large amounts of annotated training data which is impractical in pathology due to the high resolution of histopathological images. Hence, self-supervised methods have been proposed to learn features using ad-hoc pretext tasks. The self-supervised training process uses a large unlabeled dataset which makes the learning process time consuming. In this work, we propose a new method for actively sampling informative members from the training set using a small proxy network, decreasing sample requirement by 93% and training time by 62% while maintaining the same performance of the traditional self-supervised learning method. The code is available on https://github.com/Reasat/data_efficient_cl
format Preprint
id arxiv_https___arxiv_org_abs_2303_16247
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Data Efficient Contrastive Learning in Histopathology using Active Sampling
Reasat, Tahsin
Sushmit, Asif
Smith, David S.
Computer Vision and Pattern Recognition
Deep learning (DL) based diagnostics systems can provide accurate and robust quantitative analysis in digital pathology. These algorithms require large amounts of annotated training data which is impractical in pathology due to the high resolution of histopathological images. Hence, self-supervised methods have been proposed to learn features using ad-hoc pretext tasks. The self-supervised training process uses a large unlabeled dataset which makes the learning process time consuming. In this work, we propose a new method for actively sampling informative members from the training set using a small proxy network, decreasing sample requirement by 93% and training time by 62% while maintaining the same performance of the traditional self-supervised learning method. The code is available on https://github.com/Reasat/data_efficient_cl
title Data Efficient Contrastive Learning in Histopathology using Active Sampling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.16247