2 code implementations • 28 Dec 2023 • Wonjoon Chang, Dahee Kwon, Jaesik Choi
Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors.
no code implementations • 22 Sep 2022 • Wonjoon Chang, Dahee Kwon, Bumjin Park
In addition, we propose Edge-oriented Representation Network (EoREN) that can reconstruct the image with clear edges by fitting gradient information (Edge-oriented module).
