Mastering Large Scale Multi-label Image Recognition with high efficiency overCamera trap images
This work addresses the tedious and time-consuming task of image annotation in biodiversity research, offering an efficient solution for processing large datasets with limited hardware.
The paper tackled the problem of efficiently annotating large-scale camera trap images for biodiversity studies by proposing a lightweight machine learning approach that achieved 97% accuracy, surpassing human performance.
Camera traps are crucial in biodiversity motivated studies, however dealing with large number of images while annotating these data sets is a tedious and time consuming task. To speed up this process, Machine Learning approaches are a reasonable asset. In this article we are proposing an easy, accessible, light-weight, fast and efficient approach based on our winning submission to the "Hakuna Ma-data - Serengeti Wildlife Identification challenge". Our system achieved an Accuracy of 97% and outperformed the human level performance. We show that, given relatively large data sets, it is effective to look at each image only once with little or no augmentation. By utilizing such a simple, yet effective baseline we were able to avoid over-fitting without extensive regularization techniques and to train a top scoring system on a very limited hardware featuring single GPU (1080Ti) despite the large training set (6.7M images and 6TB).