« Gradient-Weighted Class Activation Mapping » : différence entre les versions
(Page créée avec « == en contruction == == Définition == XXXXX == Français == ''' XXXXXXX''' == Anglais == ''' Gradient-Weighted Class Activation Mapping''' ''' Grad-CAM''' ''Grad-CAM uses the gradient information flowing into the last convolutional layer of the model to obtain localization map and understand the importance of each pixel of the input image for a specific class.'' == Source == [https://www.geeksforgeeks.org/graceful-degradation-in-distributed-systems/ Sour... ») |
Aucun résumé des modifications |
||
| Ligne 15 : | Ligne 15 : | ||
== Source == | == Source == | ||
[https:// | [https://arxiv.org/abs/1610.02391 Source : arxiv] | ||
[https://github.com/nejlag/Grad-CAM Source : GitHub] | [https://github.com/nejlag/Grad-CAM Source : GitHub] | ||
[https://www.sciencedirect.com/topics/computer-science/ | [https://www.sciencedirect.com/topics/computer-science/gradient-weighted-class-activation-mapping Source : ScienceDirect] | ||
[[Catégorie:vocabulary]] | [[Catégorie:vocabulary]] | ||
Dernière version du 26 novembre 2024 à 20:53
en contruction
Définition
XXXXX
Français
XXXXXXX
Anglais
Gradient-Weighted Class Activation Mapping
Grad-CAM
Grad-CAM uses the gradient information flowing into the last convolutional layer of the model to obtain localization map and understand the importance of each pixel of the input image for a specific class.
Source
Contributeurs: Arianne
