Data-Efficient Classification of Birdcall Through Convolutional Neural Networks Transfer Learning
This work addresses data scarcity in niche domains like bird acoustics, but it is incremental as it applies an existing transfer learning method to a new domain.
The researchers tackled the problem of classifying birdcalls with limited training data by using transfer learning from a larger dataset to a smaller one, achieving 79% average validation accuracy on the target dataset.
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.