Image annotation for Mexican buildings database

Obeso, Abraham Montoya; Reyes, Laura Mariel Amaya; Rodríguez, Mario López; Cruz, Mario Humberto Mijes; Vázquez, Mireya Saraí García; Benois-Pineau, Jenny; Fuentes, Luis Miguel Zamudio; Martínez, Elizabeth Cano; Secundino, Jesús Abimelek Flores; Martínez, José F.; Acosta, Alejandro

doi:10.1117/12.2238352

Cited by 6 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each of the feature maps in layer k is thresholded based on the K-sigma rule to create binary maps B k ða i;j;k Þ, where i; j denote the spatial dimension of the k feature maps as shown in Eq. (26). The mean μ k and standard deviation σ k are calculated for each of the k feature maps followed by the thresholding to create k binary maps ðB k Þ. K is the parameter that controls the threshold value and is set to 1 by the authors in their work: E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 2 6 ; 1 1 6 ; 3 4 9…”

Section: Feature-based Explanation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Review of white box methods for explanations of convolutional neural networks in image classification tasks

2021

Self Cite

View full text Add to dashboard Cite

In recent years, deep learning has become prevalent to solve applications from multiple domains. Convolutional neural networks (CNNs) particularly have demonstrated state-ofthe-art performance for the task of image classification. However, the decisions made by these networks are not transparent and cannot be directly interpreted by a human. Several approaches have been proposed to explain the reasoning behind a prediction made by a network. We propose a topology of grouping these methods based on their assumptions and implementations. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision. Given the task of image classification and a trained CNN, our work aims to provide a comprehensive and detailed overview of a set of methods that can be used to create explanation maps for a particular image, which assign an importance score to each pixel of the image based on its contribution to the decision of the network. We also propose a further classification of the white box methods based on their implementations to enable better comparisons and help researchers find methods best suited for different scenarios.

show abstract

Section: Feature-based Explanation Methodsmentioning

confidence: 99%

“…Fig.7Samples showing the saliency maps for the (a) sample image, (b) gradient backpropagation, and (c) guided backpropagation methods. Sample taken from MexCulture Architectural Styles dataset 26. …”

mentioning

confidence: 99%