Efremova, Dina B., Sankupellay, Mangalam, and Konovalov, Dmitry A. (2019) Data-efficient classification of birdcall through Convolutional Neural Networks transfer learning. In: Proceedings of the International Conference on Digital Image Computing. pp. 294-301. From: DICTA 2019: International Conference on Digital Image Computing: Techniques and Applications, 2-4 December 2019, Perth, WA, Australia.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

Deep learning Convolutional Neural Network (CNN) models are powerful classification models but require a large amount of training data. In niche domains such as bird acoustics, it is expensive and difficult to obtain a large number of training samples. One method of classifying data with a limited number of training samples is to employ transfer learning. In this research, we evaluated the effectiveness of birdcall classification using transfer learning from a larger base dataset (2814 samples in 46 classes) to a smaller target dataset (351 samples in 10 classes) using the ResNet-50 CNN. We obtained 79% average validation accuracy on the target dataset in 5-fold cross-validation. The methodology of transfer learning from an ImageNet-trained CNN to a project-specific and a much smaller set of classes and images was extended to the domain of spectrogram images, where the base dataset effectively played the role of the ImageNet.

Item ID:	61471
Item Type:	Conference Item (Research - E1)
ISBN:	978-1-7281-3857-2
Copyright Information:	© 2019 IEEE
Date Deposited:	22 Jan 2020 01:12
FoR Codes:	46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461104 Neural networks @ 100%
SEO Codes:	96 ENVIRONMENT > 9608 Flora, Fauna and Biodiversity > 960899 Flora, Fauna and Biodiversity of Environments not elsewhere classified @ 100%
Downloads:	Total: 2
	More Statistics