A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks

@article{Grn2016ATA,
  title={A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks},
  author={Felix Gr{\"u}n and Christian Rupprecht and Nassir Navab and Federico Tombari},
  journal={CoRR},
  year={2016},
  volume={abs/1606.07757}
}
Over the last decade, Convolutional Neural Networks (CNN) saw a tremendous surge in performance. However, understanding what a network has learned still proves to be a challenging task. To remedy this unsatisfactory situation, a number of groups have recently proposed different methods to visualize the learned models. In this work we suggest a general taxonomy to classify and compare these methods, subdividing the literature into three main categories and providing researchers with a… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS

4 Figures & Tables

Topics

Statistics

02040201620172018
Citations per Year

Citation Velocity: 12

Averaging 12 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.