Balancing Domain Experts for Long-Tailed Camera-Trap Recognition
This addresses data imbalance issues for wildlife monitoring using camera traps, but it is incremental as it builds on existing long-tail learning methods by incorporating domain-specific characteristics.
The paper tackles long-tailed class imbalance in camera-trap recognition by proposing a framework with domain experts and a flow consistency loss, introducing two datasets (WCS-LT and DMZ-LT), and showing improved performance on recessive domain samples compared to previous methods.
Label distributions in camera-trap images are highly imbalanced and long-tailed, resulting in neural networks tending to be biased towards head-classes that appear frequently. Although long-tail learning has been extremely explored to address data imbalances, few studies have been conducted to consider camera-trap characteristics, such as multi-domain and multi-frame setup. Here, we propose a unified framework and introduce two datasets for long-tailed camera-trap recognition. We first design domain experts, where each expert learns to balance imperfect decision boundaries caused by data imbalances and complement each other to generate domain-balanced decision boundaries. Also, we propose a flow consistency loss to focus on moving objects, expecting class activation maps of multi-frame matches the flow with optical flow maps for input images. Moreover, two long-tailed camera-trap datasets, WCS-LT and DMZ-LT, are introduced to validate our methods. Experimental results show the effectiveness of our framework, and proposed methods outperform previous methods on recessive domain samples.