PuSH - Publikationsserver des Helmholtz Zentrums München

Panda, M.P.* ; Tiezzi, M.* ; Vilas, M.* ; Roig, G.* ; Eskofier, B.M. ; Zanca, D.*

FovEx: Human-inspired explanations for vision transformers and convolutional neural networks.

Int. J. Comput. Vis., DOI: 10.1007/s11263-025-02543-y (2025)
DOI
Open Access Green möglich sobald Postprint bei der ZB eingereicht worden ist.
Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods, often exhibit a strong dependence on specific model architectures. Conversely, perturbation-based methods, despite being model-agnostic, are computationally expensive as they require evaluating models on a large number of forward passes. We introduce Foveation-based Explanations (FovEx), a novel XAI method inspired by human vision, which combines biologically inspired foveation-based transformations with gradient-driven overt attention to iteratively select locations of interest. These locations are selected to maximize the performance of the model to be explained with respect to the downstream task and then combined to generate an attribution map. We provide a thorough evaluation with qualitative and quantitative assessments on established benchmarks. Our method achieves state-of-the-art performance on both transformers (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility among various architectures. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14% in NSS compared to RISE, +203% in NSS compared to GradCAM). This comparison enhances our confidence in FovEx's ability to close the interpretation gap between humans and machines.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Human-inspired; Attribution Maps; Explainable Artificial Intelligence; Transformers; CNNs; Visual Explanations
ISSN (print) / ISBN 0920-5691
e-ISSN 1573-1405
Zeitschrift International Journal of Computer Vision
Verlag Springer
Verlagsort Van Godewijckstraat 30, 3311 Gz Dordrecht, Netherlands
Begutachtungsstatus Peer reviewed
Institut(e) Human-Centered AI (HCA)