Evolving optimum camouflage with Generative Adversarial Networks
Preprint
Abstract
We describe a novel method to exploit Generative Adversarial Networks to simulate an evolutionary arms race between the camouflage of a synthetic prey and its predator. Patterns evolved using our methods are shown to provide progressively more effective concealment and outperform two recognised camouflage techniques. The method will be invaluable, particularly for biologists, for rapidly developing and testing optimal camouflage or signalling patterns in multiple environments.Keywords
All Related Versions
- Published version: Methods in Ecology and Evolution, 11 (2), 240.
This publication has 13 references indexed in Scilit:
- Generative Adversarial Networks: An OverviewIEEE Signal Processing Magazine, 2018
- Optimal background matching camouflageProceedings Of The Royal Society B-Biological Sciences, 2017
- How camouflage worksPhilosophical Transactions of the Royal Society B: Biological Sciences, 2017
- Quantifying camouflage: how to predict detectability from appearanceBMC Ecology and Evolution, 2017
- Colour Polymorphism Protects Prey Individuals and Populations Against PredationScientific Reports, 2016
- Evolution of colour vision in mammalsPhilosophical Transactions of the Royal Society B: Biological Sciences, 2009
- The re-emergence of felid camouflage with the decay of predator recognition in deer under relaxed selectionProceedings Of The Royal Society B-Biological Sciences, 2006
- Disruptive coloration and background pattern matchingNature, 2005
- Visual predators select for crypticity and polymorphism in virtual preyNature, 2002
- The Logic of Animal ConflictNature, 1973