发布时间:
2021-02-23 00:00:00
期刊:
PNAS
doi: 10.1073/pnas.2011417118
作者:
Johannes Mehrer,Courtney J. Spoerer,Emer C. Jones,Nikolaus Kriegeskorte,Tim C. Kietzmann
摘要:
Inspired by core principles of information processing in the brain, deep neural networks (DNNs) have demonstrated remarkable success in computer vision applications. At the same time, networks trained on the task of object classification exhibit similarities to representations found in the primate visual system. This result is surprising because the datasets commonly used for training are designed to be engineering challenges. Here, we use linguistic corpus statistics and human concreteness ratings as guiding principles to design a resource that more closely mirrors categories that are relevant to humans. The result is ecoset, a collection of 1.5 million images from 565 basic-level categories. We show that ecoset-trained DNNs yield better models of human higher-level visual cortex and human behavior.
All materials presented in this paper (ecoset dataset, pretrained networks, and test stimuli) are openly available for research purposes via CodeOcean ([52][1]):
.
[1]: #ref-52