AUTHOR=Tuggener Lukas , Schmidhuber Jürgen , Stadelmann Thilo TITLE=Is it enough to optimize CNN architectures on ImageNet? JOURNAL=Frontiers in Computer Science VOLUME=4 YEAR=2022 URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2022.1041703 DOI=10.3389/fcomp.2022.1041703 ISSN=2624-9898 ABSTRACT=
Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train 500 CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as 8 additional well-known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highly