Two-phase training mitigates class imbalance for camera trap image classification with CNNs

TL;DR

This paper introduces a two-phase training method to address class imbalance in camera trap image classification with CNNs, significantly improving minority class performance while maintaining overall accuracy.

Contribution

The study demonstrates that two-phase training, combining oversampling and undersampling, enhances minority class F1-scores and outperforms single-method approaches in imbalanced ecological datasets.

Findings

Two-phase training increases minority class F1-scores by up to 3.0%.

It outperforms oversampling or undersampling alone by 6.1% in F1-score.

Combining over- and undersampling yields better results than using either alone.

Abstract

By leveraging deep learning to automatically classify camera trap images, ecologists can monitor biodiversity conservation efforts and the effects of climate change on ecosystems more efficiently. Due to the imbalanced class-distribution of camera trap datasets, current models are biased towards the majority classes. As a result, they obtain good performance for a few majority classes but poor performance for many minority classes. We used two-phase training to increase the performance for these minority classes. We trained, next to a baseline model, four models that implemented a different versions of two-phase training on a subset of the highly imbalanced Snapshot Serengeti dataset. Our results suggest that two-phase training can improve performance for many minority classes, with limited loss in performance for the other classes. We find that two-phase training based on majority undersampling increases class-specific F1-scores up to 3.0%. We also find that two-phase training outperforms using only oversampling or undersampling by 6.1% in F1-score on average. Finally, we find that a combination of over- and undersampling leads to a better performance than using them individually.