Bag of tricks for long-tail visual recognition of animal species in camera-trap images

Abstract

Camera traps are a method for monitoring wildlife and they collect a large number of pictures. The number of images collected of each species usually follows a long-tail distribution, i.e., a few classes have a large number of instances, while a lot of species have just a small percentage. Although in most cases these rare species are the ones of interest to ecologists, they are often neglected when using deep-learning models because these models require a large number of images for the training. In this work, a simple and effective framework called Square-Root Sampling Branch (SSB) is proposed, which combines two classification branches that are trained using square-root sampling and instance sampling to improve long-tail visual recognition, and this is compared to state-of-the-art methods for handling this task: square-root sampling, class-balanced focal loss, and balanced group softmax. To achieve a more general conclusion, the methods for handling long-tail visual recognition were systematically evaluated in four families of computer vision models (ResNet, MobileNetV3, EfficientNetV2, and Swin Transformer) and four camera-trap datasets with different characteristics. Initially, a robust baseline with the most recent training tricks was prepared and, then, the methods for improving long-tail recognition were applied. Our experiments show that square-root sampling was the method that most improved the performance for minority classes by around 15%; however, this was at the cost of reducing the majority classes' accuracy by at least 3%. Our proposed framework (SSB) demonstrated itself to be competitive with the other methods and achieved the best or the second-best results for most of the cases for the tail classes; but, unlike the square-root sampling, the loss in the performance of the head classes was minimal, thus achieving the best trade-off among all the evaluated methods. Our experiments also show that Swin Transformer can achieve high performance for rare classes without applying any additional method for handling imbalance, and attains an overall accuracy of 88.76% for the WCS dataset and 94.97% for Snapshot Serengeti using a location-based training/test partition. Despite the improvement in the tail classes' performance, our experiments highlight the need for better methods for handling long-tail visual recognition in camera-trap images, since state-of-the-art approaches achieve poor performance, especially in classes with just a few training instances.