Controlling explanatory heatmap resolution and semantics via decomposition depth

@article{Bach2016ControllingEH,
  title={Controlling explanatory heatmap resolution and semantics via decomposition depth},
  author={Sebastian Bach and Alexander Binder and Klaus-Robert M{\"u}ller and Wojciech Samek},
  journal={2016 IEEE International Conference on Image Processing (ICIP)},
  year={2016},
  pages={2271-2275}
}
We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps. Layer-wise Relevance Propagation (LRP) is a method to compute scores for individual components of an input image, denoting their contribution to the prediction of the classifier for one particular test point. We… CONTINUE READING
8
Twitter Mentions

Similar Papers

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Distinctive Image Features from Scale-Invariant Keypoints

  • International Journal of Computer Vision
  • 2004
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Analyzing Classifiers: Fisher Vectors and Deep Neural Networks

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Caffe: An open source convolutional architecture for fast feature embedding

Yangqing Jia
  • http://caffe.berkeleyvision.org/, 2013.
  • 2013
VIEW 1 EXCERPT