loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Felipe Figueroa 1 ; Hanwei Zhang 1 ; Ronan Sicre 1 ; Yannis Avrithis 2 and Stephane Ayache 1

Affiliations: 1 Centrale Marseille, Aix Marseille Univ., CNRS, LIS, Marseille, France ; 2 Institute of Advanced Research on Artificial Intelligence (IARAI), Austria

Keyword(s): Gradient, Guided Backpropagation, Class Activation Maps, Interpretability.

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.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.235.145.252

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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; ISSN 2184-4321, SciTePress, pages 757-764. DOI: 10.5220/0012466800003660

@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},
issn={2184-4321},
}

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
IS - 2184-4321
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