A New Method to Visualize Deep Neural Networks
By Luisa M. Zintgraf, Taco Cohen, Max Welling. 2016
48 citations recorded by the source corpus.
We present a method for visualising the response of a deep neural network to a specific input. For image data for instance our method will highlight areas that provide evidence in favor of, and against choosing a certain class. The method overcomes several shortcomings of previous methods and provides great additional insight into the decision making process of convolutional networks, which is important both to improve models and to accelerate the adoption of such methods in e.g. medicine. In experiments on ImageNet data, we illustrate how the method works and can be applied in different ways to understand deep neural nets.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Wojciech Samek
- K. Müller
- Grgoire Montavon
- Sebastian Lapuschkin
- Alexander Binder
- Christopher J. Anders
- Longo Luca
- Giulia Vilone
In Computer Vision and Pattern Recognition
- Wojciech Samek
- K. Müller
- Grgoire Montavon
- Sebastian Lapuschkin
- Alexander Binder
- Lin F. Yang
- Zizhao Zhang
- Christopher J. Anders
Citations in the corpus
- Understanding and Comparing Deep Neural Networks for Age and Gender Classification (2017, methodology): “Several methods for explaining individual predictions have emerged since then, with robust yet computationally expensive occlusion-based [44] and samplingbased analysis [31, 45], (gradient-based) sensitivity analysis [14, 5, 38] and backpropagation-type approaches [3, 44, 26] among them.”
- Visualizations of Deep Neural Networks in Computer Vision: A Survey (2017, methodology): “Zintgraf [86] 2016 Architecture assessment Pixel displays, HeatMaps Classification DCNN ILSVRC”
- MDNet: A Semantically and Visually Interpretable Medical Image Diagnosis Network (2017, background): “We witness growing interests of its exploration to achieve the network interpretability [41, 27].”
- DeepClue: Visual Interpretation of Text-Based Deep Stock Prediction (2019, background): “[19] developed an elaborate conditional sampling algorithm to analyze how deep neural networks”
- Identifying Individual Facial Expressions by Deconstructing a Neural Network (2016, methodology): “Explanation methods such as [3,26,22,12,13,7,27,25,19] have been able to successfully solve this important open problem.”