HackerPapers

arXiv:1603.02518cs.CV

A New Method to Visualize Deep Neural Networks

Luisa M. Zintgraf, Taco S. Cohen, Max Welling

Abstract

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.

arXiv comments
Please note that this version of the article is outdated. The new version (published at ICLR2017) includes additional experiments on MRI scans and can be found at arXiv:1702.04595
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Sep 2016 to Feb 2018.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. The crisis of American forensics 1 comment

    • https://arxiv.org/abs/1711.09784 https://arxiv.org/abs/1708.01785 https://arxiv.org/abs/1710.00935 https://arxiv.org/abs/1702.04595 https://arxiv.org/abs/1801.01693 https://arxiv.org/abs/1503.02531 https://arxiv.org/abs/1712.03781 https://arxiv.org/abs/1710.07535…

      sovok_xView on HNParent context

  2. Explainable Artificial Intelligence (XAI) Darpa Funding 1 comment

    • Bringing some form of feature introspection to deep neural networks will probably involve clever ways of visualizing the feature activations of unstructured data https://arxiv.org/abs/1603.02518

      vonnikView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.