Communication Dans Un Congrès Année : 2024

The Do's and Don'ts of Grad-CAM in Image Segmentation as demonstrated on the Synapse multi-organ CT Dataset

Résumé

The field of eXplainable Artificial Intelligence (xAI) has drawn an immense interest over the last decade. This interest, however, is almost exclusively focused on image classification, whereas other computer vision domains have remained relatively neglected. Recently, however, methods developed in the context of image classification have been extended to other domains such as image segmentation. One such method is Seg-Grad-CAM which is an extension of Grad-CAM. The present paper aims to highlight some of the nuances associated with the utilization of Seg-Grad-CAM in order to generate saliency maps for image segmentation, and instead highlights an alternate application, namely investigating information flow, which can better utilize the capabilities of Seg-Grad-CAM and similar methods. Sample demonstration is provided on an image from the Synapse multi-organ CT dataset.

Fichier principal
Vignette du fichier
163_The_Do_s_and_Don_ts_of_Gra.pdf (632.41 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05370301 , version 1 (18-11-2025)

Licence

Identifiants

  • HAL Id : hal-05370301 , version 1

Citer

Syed Nouman Hasany, Fabrice Mériaudeau, Caroline Petitjean. The Do's and Don'ts of Grad-CAM in Image Segmentation as demonstrated on the Synapse multi-organ CT Dataset. Medical Imaging with Deep Learning, Jul 2024, Paris, France. ⟨hal-05370301⟩
170 Consultations
90 Téléchargements

Partager

  • More