Data-Efficient Classification of Birdcall Through Convolutional Neural Networks Transfer Learning

TL;DR

This paper demonstrates that transfer learning with CNNs, specifically ResNet-50, can effectively classify birdcalls with limited data, achieving 79% accuracy by leveraging a larger related dataset.

Contribution

It extends transfer learning techniques from ImageNet to spectrogram images for birdcall classification, showing effectiveness with small datasets.

Findings

Achieved 79% validation accuracy on small birdcall dataset

Validated transfer learning from larger datasets to niche acoustic domains

Extended CNN transfer learning methodology to spectrogram images

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.