To crop or not to crop: Comparing whole‐image and cropped classification on a large dataset of camera trap images

Today's article comes from the IET Computer Vision journal. The authors are Gadot et al., from Google. In this paper they attempt to settle a debate that's raged in computer-vision circles for years: Which kind of classifier is better for camera-traps, one-stage or two?

DOI: 10.1049/cvi2.12318