GAP: Quantifying the generative adversarial set and class feature applicability of deep neural networks
Document Type
Conference Proceeding
Publication Date
1-1-2020
Abstract
Recent work in deep neural networks has sought to characterize the nature in which a network learns features and how applicable learnt features are to various problem sets. Deep neural network applicability can be split into three sub-problems; set applicability, class applicability, and instance applicability. In this work we seek to quantify the applicability of features learned during adversarial training, focusing specifically on set and class applicability. We apply techniques for measuring applicability to both generators and discriminators trained on various data sets to quantify applicability.
Publication Source (Journal or Book title)
Proceedings International Conference on Pattern Recognition
First Page
8384
Last Page
8391
Recommended Citation
Collier, E., & Mukhopadhyay, S. (2020). GAP: Quantifying the generative adversarial set and class feature applicability of deep neural networks. Proceedings International Conference on Pattern Recognition, 8384-8391. https://doi.org/10.1109/ICPR48806.2021.9412665