Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/264999
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Generating attribution maps with disentangled masked backpropagation |
Autor: | Ruiz Ovejero, Adrià CSIC; Agudo, Antonio CSIC ORCID ; Moreno-Noguer, Francesc CSIC ORCID | Fecha de publicación: | 2021 | Citación: | International Conference on computer Vision 1: 905-914 (2021) | Resumen: | Attribution map visualization has arisen as one of the most effective techniques to understand the underlying inference process of Convolutional Neural Networks. In this task, the goal is to compute an score for each image pixel related to its contribution to the network output. In this paper, we introduce Disentangled Masked Backpropagation (DMBP), a novel gradient-based method that leverages on the piecewise linear nature of ReLU networks to decompose the model function into different linear mappings. This decomposition aims to disentangle the attribution maps into positive, negative and nuisance factors by learning a set of variables masking the contribution of each filter during back-propagation. A thorough evaluation over standard architectures (ResNet50 and VGG16) and benchmark datasets (PASCAL VOC and ImageNet) demonstrates that DMBP generates more visually interpretable attribution maps than previous approaches. Additionally, we quantitatively show that the maps produced by our method are more consistent with the true contribution of each pixel to the final network output. | Descripción: | Trabajo presentado en la International Conference on Computer Vision (ICCV), celebrada de forma virtual del 11 al 17 de octubre de 2021 | URI: | http://hdl.handle.net/10261/264999 | DOI: | 10.1109/ICCV48922.2021.00094 | Identificadores: | issn: 1550-5499 |
Aparece en las colecciones: | (IRII) Artículos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Ruiz_Generating_Attribution_Maps_With_Disentangled_Masked_Backpropagation_ICCV_2021_paper.pdf | 7,56 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
38
checked on 05-may-2024
Download(s)
88
checked on 05-may-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.