Skip to main content
main-content
Top

Hint

Swipe to navigate through the articles of this issue

23-12-2017 | Issue 10/2018

International Journal of Computer Vision 10/2018

Top-Down Neural Attention by Excitation Backprop

Journal:
International Journal of Computer Vision > Issue 10/2018
Authors:
Jianming Zhang, Sarah Adel Bargal, Zhe Lin, Jonathan Brandt, Xiaohui Shen, Stan Sclaroff
Important notes
Communicated by Jiri Matas, Bastian Leibe, Max Welling and Nicu Sebe.

Electronic supplementary material

The online version of this article (https://​doi.​org/​10.​1007/​s11263-017-1059-x) contains supplementary material, which is available to authorized users.

Abstract

We aim to model the top-down attention of a convolutional neural network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process. Furthermore, we introduce the concept of contrastive attention to make the top-down attention maps more discriminative. We show a theoretic connection between the proposed contrastive attention formulation and the Class Activation Map computation. Efficient implementation of Excitation Backprop for common neural network layers is also presented. In experiments, we visualize the evidence of a model’s classification decision by computing the proposed top-down attention maps. For quantitative evaluation, we report the accuracy of our method in weakly supervised localization tasks on the MS COCO, PASCAL VOC07 and ImageNet datasets. The usefulness of our method is further validated in the text-to-region association task. On the Flickr30k Entities dataset, we achieve promising performance in phrase localization by leveraging the top-down attention of a CNN model that has been trained on weakly labeled web images. Finally, we demonstrate applications of our method in model interpretation and data annotation assistance for facial expression analysis and medical imaging tasks.

Please log in to get access to this content

To get access to this content you need the following product:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit dem Kombi-Abo erhalten Sie vollen Zugriff auf über 1,8 Mio. Dokumente aus mehr als 61.000 Fachbüchern und rund 500 Fachzeitschriften aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe

Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit dem Wirtschafts-Abo erhalten Sie Zugriff auf über 1 Mio. Dokumente aus mehr als 45.000 Fachbüchern und 300 Fachzeitschriften aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb

Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit dem Technik-Abo erhalten Sie Zugriff auf über 1 Mio. Dokumente aus mehr als 40.000 Fachbüchern und 300 Fachzeitschriften aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Maschinenbau + Werkstoffe

Testen Sie jetzt 30 Tage kostenlos.

Supplementary Material
Supplementary material 1 (pdf 18049 KB)
11263_2017_1059_MOESM1_ESM.pdf
Literature
About this article

Other articles of this Issue 10/2018

International Journal of Computer Vision 10/2018 Go to the issue

Premium Partner

image credits