Alzantot, M;
Widdicombe, A;
Julier, S;
Srivastava, M;
(2019)
NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning.
In:
2019 IEEE International Conference on Smart Computing (SMARTCOMP).
(pp. pp. 81-86).
IEEE: Washington, DC, USA.
Preview |
Text
1908.04389v1.pdf - Published Version Download (3MB) | Preview |
Abstract
Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explanation of classification model results. When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model. The mask values are tuned by minimizing a properly designed cost function that preserves the classification result and encourages producing an interpretable mask. Experiments using state-of-art Convolutional Neural Networks for image recognition on different datasets (CIFAR-10 and ImageNet) show that NeuroMask successfully localizes the parts of the input image which are most relevant to the DNN decision. By showing a visual quality comparison between NeuroMask explanations and those of other methods, we find NeuroMask to be both accurate and interpretable.
| Type: | Proceedings paper |
|---|---|
| Title: | NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning |
| Event: | 5th IEEE International Conference on Smart Computing (SMARTCOMP) |
| Location: | Washington, DC |
| Dates: | 12 June 2019 - 14 June 2019 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/SMARTCOMP.2019.00033 |
| Publisher version: | https://doi.org/10.1109/SMARTCOMP.2019.00033 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Computational modeling , Predictive models, Training, Cost function, Neural networks, Computer science, Image recognition |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10119535 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
