An Interactive Visualization for Feature Localization in Deep Neural Networks

Zurowietz M, Nattkemper TW (2020)
Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence 3: 49.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA 3.29 MB
Abstract / Bemerkung
Deep artificial neural networks have become the go-to method for many machine learning tasks. In the field of computer vision, deep convolutional neural networks achieve state-of-the-art performance for tasks such as classification, object detection or instance segmentation. As deep neural networks become more and more complex, their inner workings become more and more opaque, rendering them a "black box" whose decision making process is no longer comprehensible. In recent years, various methods have been presented that attempt to peek inside the black box and to visualize the inner workings of deep neural networks, with a focus on deep convolutional neural networks for computer vision. These methods can serve as a toolbox to facilitate the design and inspection of neural networks for computer vision and the interpretation of the decision making process of the network. Here, we present the new tool Interactive Feature Localization in Deep neural networks (IFeaLiD) which provides a novel visualization approach to convolutional neural network layers. The tool interprets neural network layers as multivariate feature maps and visualizes the similarity between the feature vectors of individual pixels of an input image in a heat map display. The similarity display can reveal how the input image is perceived by different layers of the network and how the perception of one particular image region compares to the perception of the remaining image. IFeaLiD runs interactively in a web browser and can process even high resolution feature maps in real time by using GPU acceleration with WebGL 2. We present examples from four computer vision datasets with feature maps from different layers of a pre-trained ResNet101. IFeaLiD is open source and available online at https://ifealid.cebitec.uni-bielefeld.de.
Erscheinungsjahr
2020
Zeitschriftentitel
Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence
Band
3
Art.-Nr.
49
eISSN
2624-8212
Page URI
https://pub.uni-bielefeld.de/record/2943901

Zitieren

Zurowietz M, Nattkemper TW. An Interactive Visualization for Feature Localization in Deep Neural Networks. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence . 2020;3: 49.
Zurowietz, M., & Nattkemper, T. W. (2020). An Interactive Visualization for Feature Localization in Deep Neural Networks. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence , 3, 49. doi:10.3389/frai.2020.00049
Zurowietz, M., and Nattkemper, T. W. (2020). An Interactive Visualization for Feature Localization in Deep Neural Networks. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence 3:49.
Zurowietz, M., & Nattkemper, T.W., 2020. An Interactive Visualization for Feature Localization in Deep Neural Networks. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence , 3: 49.
M. Zurowietz and T.W. Nattkemper, “An Interactive Visualization for Feature Localization in Deep Neural Networks”, Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence , vol. 3, 2020, : 49.
Zurowietz, M., Nattkemper, T.W.: An Interactive Visualization for Feature Localization in Deep Neural Networks. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence . 3, : 49 (2020).
Zurowietz, Martin, and Nattkemper, Tim Wilhelm. “An Interactive Visualization for Feature Localization in Deep Neural Networks”. Frontiers in Artificial Intelligence - Machine Learning and Artificial Intelligence 3 (2020): 49.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2020-07-31T07:03:40Z
MD5 Prüfsumme
cff6843a28d8245efd519059aa74f95b

Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar