This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.
@article{arxiv.1906.01150,
title = {Breaking Inter-Layer Co-Adaptation by Classifier Anonymization},
author = {Ikuro Sato and Kohta Ishikawa and Guoqing Liu and Masayuki Tanaka},
journal= {arXiv preprint arXiv:1906.01150},
year = {2019}
}