USP Electronic Research Repository

Feature map upscaling to improve scale invariance in convolutional neural networks

Kumar, Dinesh and Sharma, Dharmendra P. (2023) Feature map upscaling to improve scale invariance in convolutional neural networks. Journal of Artificial Intelligence and Soft Computing Research, 13 (1). pp. 51-74. ISSN 2449-6499

Full text not available from this repository. (Request a copy)

Abstract

Introducing variation in the training dataset through data augmentation has been a popular technique to make Convolutional Neural Networks (CNNs) spatially invariant but leads to increased dataset volume and computation cost. Instead of data augmentation, augmentation of feature maps is proposed to introduce variations in the features extracted by a CNN. To achieve this, a rotation transformer layer called Rotation Invariance Transformer (RiT) is developed, which applies rotation transformation to augment CNN features. The RiT layer can be used to augment output features from any convolution layer within a CNN. However, its maximum effectiveness is shown when placed at the output end of final convolution layer. We test RiT in the
application of scale-invariance where we attempt to classify scaled images from benchmark datasets. Our results show promising improvements in the networks ability to be scale invariant whilst keeping the model computation cost low.

Item Type: Journal Article
Additional Information: Accepted for publication - 25 July 2022 To be published in January, 2023
Subjects: Q Science > Q Science (General) > Q350-390 Information theory
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: School of Information Technology, Engineering, Mathematics and Physics (STEMP)
Depositing User: Dinesh Kumar
Date Deposited: 06 Jan 2023 03:10
Last Modified: 06 Jan 2023 03:10
URI: https://repository.usp.ac.fj/id/eprint/13824

Actions (login required)

View Item View Item