Adapting Deep Network Features to Capture Psychological Representations: An Abridged Report
Abstract
Deep neural networks have become increasingly successful at solving classic perception problems (e.g., recognizing objects), often reaching or surpassing human-level accuracy. In this abridged report of Peterson et al. [2016], we examine the relationship between the image representations learned by these networks and those of humans. We find that deep features learned in service of object classification account for a significant amount of the variance in human similarity judgments for a set of animal images. However, these features do not appear to capture some key qualitative aspects of human representations. To close this gap, we present a method for adapting deep features to align with human similarity judgments, resulting in image representations that can potentially be used to extend the scope of psychological experiments and inform human-centric AI.
Cite
Text
Peterson et al. "Adapting Deep Network Features to Capture Psychological Representations: An Abridged Report." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/697Markdown
[Peterson et al. "Adapting Deep Network Features to Capture Psychological Representations: An Abridged Report." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/peterson2017ijcai-adapting/) doi:10.24963/IJCAI.2017/697BibTeX
@inproceedings{peterson2017ijcai-adapting,
title = {{Adapting Deep Network Features to Capture Psychological Representations: An Abridged Report}},
author = {Peterson, Joshua C. and Abbott, Joshua T. and Griffiths, Thomas L.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {4934-4938},
doi = {10.24963/IJCAI.2017/697},
url = {https://mlanthology.org/ijcai/2017/peterson2017ijcai-adapting/}
}