User Loss A Forced-Choice-Inspired Approach to Train Neural Networks Directly by User Interaction

Zarei S, Stimpel B, Syben-Leisner C, Maier A (2019)

Publication Type: Conference contribution

Publication year: 2019

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Publisher: Springer Berlin Heidelberg

Pages Range: 92-97

Conference Proceedings Title: Informatik aktuell

Event location: Lübeck DE

ISBN: 9783658253257

DOI: 10.1007/978-3-658-25326-4_22

Abstract

In this paper, we investigate whether is it possible to train a neural network directly from user inputs. We consider this approach to be highly relevant for applications in which the point of optimality is not well-defined and user-dependent. Our application is medical image denoising which is essential in fluoroscopy imaging. In this field every user, i.e. physician, has a different flavor and image quality needs to be tailored towards each individual. To address this important problem, we propose to construct a loss function derived from a forced-choice experiment. In order to make the learning problem feasible, we operate in the domain of precision learning, i.e., we inspire the network architecture by traditional signal processing methods in order to reduce the number of trainable parameters. The algorithm that was used for this is a Laplacian pyramid with only six trainable parameters. In the experimental results, we demonstrate that two image experts who prefer different filter characteristics between sharpness and de-noising can be created using our approach. Also models trained for a specific user perform best on this users test data. This approach opens the way towards implementation of direct user feedback in deep learning and is applicable for a wide range of application.

Authors with CRIS profile

Bernhard Stimpel Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) Christopher Syben Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Zarei, S., Stimpel, B., Syben-Leisner, C., & Maier, A. (2019). User Loss A Forced-Choice-Inspired Approach to Train Neural Networks Directly by User Interaction. In Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff (Eds.), Informatik aktuell (pp. 92-97). Lübeck, DE: Springer Berlin Heidelberg.

MLA:

Zarei, Shahab, et al. "User Loss A Forced-Choice-Inspired Approach to Train Neural Networks Directly by User Interaction." Proceedings of the Workshop on Bildverarbeitung fur die Medizin, 2019, Lübeck Ed. Thomas M. Deserno, Andreas Maier, Christoph Palm, Heinz Handels, Klaus H. Maier-Hein, Thomas Tolxdorff, Springer Berlin Heidelberg, 2019. 92-97.

BibTeX: Download