A model-agnostic active learning approach for animal detection from camera traps

TL;DR

This paper introduces a model-agnostic active learning method for animal detection in camera trap images, effectively reducing labeled data requirements while maintaining high detection performance.

Contribution

It presents a novel active learning approach that combines uncertainty and diversity measures at multiple levels, applicable without full model access.

Findings

Achieves comparable detection performance using only 30% of training data

Validates approach on a benchmark animal dataset

Enhances wildlife monitoring efficiency

Abstract

Smart data selection is becoming increasingly important in data-driven machine learning. Active learning offers a promising solution by allowing machine learning models to be effectively trained with optimal data including the most informative samples from large datasets. Wildlife data captured by camera traps are excessive in volume, requiring tremendous effort in data labelling and animal detection models training. Therefore, applying active learning to optimise the amount of labelled data would be a great aid in enabling automated wildlife monitoring and conservation. However, existing active learning techniques require that a machine learning model (i.e., an object detector) be fully accessible, limiting the applicability of the techniques. In this paper, we propose a model-agnostic active learning approach for detection of animals captured by camera traps. Our approach integrates uncertainty and diversity quantities of samples at both the object-based and image-based levels into the active learning sample selection process. We validate our approach in a benchmark animal dataset. Experimental results demonstrate that, using only 30% of the training data selected by our approach, a state-of-the-art animal detector can achieve a performance of equal or greater than that with the use of the complete training dataset.