Extending Contrastive Learning to Unsupervised Redundancy Identification

Modern deep neural network (DNN)-based approaches have delivered great performance for computer vision tasks; however, they require a massive annotation cost due to their data-hungry nature. Hence, given a fixed budget and unlabeled examples, improving the quality of examples to be annotated is a cl...

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Jeongwoo Ju, Heechul Jung, Junmo Kim
Format:	Article
Language:	English
Published:	MDPI AG 2022-02-01
Subjects:	deep learning redundancy identification convolutional neural network (CNN) semantic segmentation object detection
Online Access:	https://www.mdpi.com/2076-3417/12/4/2201