Testing the equivalency of human "predators" and deep neural networks in the detection of cryptic moths.

Abstract

Researchers have shown growing interest in using deep neural networks (DNNs) to efficiently test the effects of perceptual processes on the evolution of color patterns and morphologies. Whether this is a valid approach remains unclear, as it is unknown whether the relative detectability of ecologically relevant stimuli to DNNs actually matches that of biological neural networks. To test this, we compare image classification performance by humans and six DNNs (AlexNet, VGG-16, VGG-19, ResNet-18, SqueezeNet, and GoogLeNet) trained to detect artificial moths on tree trunks. Moths varied in their degree of crypsis, conferred by different sizes and spatial configurations of transparent wing elements. Like humans, four of six DNN architectures found moths with larger transparent elements harder to detect. However, humans and only one DNN architecture (GoogLeNet) found moths with transparent elements touching one side of the moth's outline harder to detect than moths with untouched outlines. When moths were small, the camouflaging effect of transparent elements touching the moth's outline was reduced for DNNs but enhanced for humans. Prey size can thus interact with camouflage type in opposing directions in humans and DNNs, which warrants a deeper investigation of size interactions with a broader range of stimuli. Overall, our results suggest that humans and DNNs responses had some similarities, but not enough to justify the widespread use of DNNs for studies of camouflage.