XtremeAugment: Getting More From Your Data Through Combination of Image Collection and Image Augmentation

XtremeAugment: Getting More From Your Data Through Combination of Image Collection and Image Augmentation

Deep convolutional neural networks are highly efficient for computer vision tasks using plenty of training data. However, there remains a problem of small training datasets. For addressing this problem the training pipeline which handles rare object types and an overall lack of training data to buil...

Full description

Bibliographic Details
Main Authors: Sergey Nesteruk, Svetlana Illarionova, Timur Akhtyamov, Dmitrii Shadrin, Andrey Somov, Mariia Pukalchik, Ivan Oseledets
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Image augmentation
computer vision
image segmentation
data collection
Internet of Things
few-shot learning
Online Access:https://ieeexplore.ieee.org/document/9721254/

Internet

https://ieeexplore.ieee.org/document/9721254/

Similar Items