CamoGAN: Evolving optimum camouflage with Generative Adversarial Networks

Autor:	Roland J. Baddeley, John G. Fennell, Nicholas E. Scott-Samuel, Innes C. Cuthill, Karin Kjernsmo, Laszlo Talas
Rok vydání:	2019
Předmět:	Computer science business.industry Ecological Modeling Deep learning Adversarial system Camouflage Visual Perception Cognitive Science Artificial intelligence business Ecology Evolution Behavior and Systematics Generative grammar
Zdroj:	Talas, L, Fennell, J, Kjernsmo, K, Cuthill, I, Scott-Samuel, N & Baddeley, R 2020, ' CamoGAN : Evolving optimum camouflage with Generative Adversarial Networks ', Methods in Ecology and Evolution, vol. 11, no. 2, pp. 240-247 . https://doi.org/10.1111/2041-210X.13334
ISSN:	2041-210X
DOI:	10.1111/2041-210x.13334
Popis:	1. One of the most challenging issues in modelling the evolution of protective colouration is the immense number of potential combinations of colours and textures.2. We describe CamoGAN, a novel method to exploit Generative Adversarial Networks to simulate an evolutionary arms race between the camouflage of a synthetic prey and its predator.3. Patterns evolved using our methods are shown to provide progressively more effective concealment and outperform two recognised camouflage techniques, as validated by using humans as visual predators.4. We believe CamoGAN will be highly useful, particularly for biologists, for rapidly developing and testing optimal camouflage or signalling patterns in multiple environments.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77133d84dad380badd41efc1ddcbbe68 https://doi.org/10.1111/2041-210x.13334 Zobrazit plný text záznamu Plný text