Skip to Main content Skip to Navigation
Conference papers

Towards Interpretability of Segmentation Networks by analyzing DeepDreams

Vincent Couteaux O. Nempont Guillaume Pizaine Isabelle Bloch 1, 2
1 IMAGES - Image, Modélisation, Analyse, GEométrie, Synthèse
LTCI - Laboratoire Traitement et Communication de l'Information
2 IDS - Département Images, Données, Signal
Abstract : Interpretability of a neural network can be expressed as the identification of patterns or features to which the network can be either sensitive or indifferent. To this aim, a method inspired by DeepDream is proposed, where the activation of a neuron is maximized by performing gradient ascent on an input image. The method outputs curves that show the evolution of features during the maximization. A controlled experiment show how it enables assess the robustness to a given feature, or by contrast its sensitivity. The method is illustrated on the task of segmenting tumors in liver CT images.
Keywords : Interpretability Deep Learning DeepDream Segmentation Liver CT images
Document type :
Conference papers
Complete list of metadata
https://hal.telecom-paris.fr/hal-02288076
Contributor : Telecomparis Hal <>
Submitted on : Friday, September 13, 2019 - 5:39:19 PM
Last modification on : Wednesday, October 14, 2020 - 4:14:34 AM

Identifiers

  • HAL Id : hal-02288076, version 1

Collections

LTCI | PARISTECH | INSTITUT-TELECOM | IDS | IMAGES

Citation

Vincent Couteaux, O. Nempont, Guillaume Pizaine, Isabelle Bloch. Towards Interpretability of Segmentation Networks by analyzing DeepDreams. iMIMIC Workshop at MICCAI 2019: Interpretability of Machine Intelligence in Medical Image Computing, 2019, Shenzhen, China. pp.56-63. ⟨hal-02288076⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

185