A Learning Paradigm for Interpretable Gradients

Felipe Figueroa, Hanwei Zhang, Ronan Sicre, Yannis Avrithis, Stephane Ayache

2024

Abstract

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation. However, it is well understood that gradients are noisy and alternatives like guided backpropagation have been proposed to obtain better visualization at inference. In this work, we present a novel training approach to improve the quality of gradients for interpretability. In particular, we introduce a regularization loss such that the gradient with respect to the input image obtained by standard backpropagation is similar to the gradient obtained by guided backpropagation. We find that the resulting gradient is qualitatively less noisy and improves quantitatively the interpretability properties of different networks, using several interpretability methods.

Paper Citation

in Harvard Style

Figueroa F., Zhang H., Sicre R., Avrithis Y. and Ayache S. (2024). A Learning Paradigm for Interpretable Gradients. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 757-764. DOI: 10.5220/0012466800003660

in Bibtex Style

@conference{visapp24,
author={Felipe Figueroa and Hanwei Zhang and Ronan Sicre and Yannis Avrithis and Stephane Ayache},
title={A Learning Paradigm for Interpretable Gradients},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={757-764},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012466800003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - A Learning Paradigm for Interpretable Gradients
SN - 978-989-758-679-8
AU - Figueroa F.
AU - Zhang H.
AU - Sicre R.
AU - Avrithis Y.
AU - Ayache S.
PY - 2024
SP - 757
EP - 764
DO - 10.5220/0012466800003660
PB - SciTePress