Using a model of human visual perception to improve deep learning.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Deep learning algorithms achieve human-level (or better) performance on many tasks, but there still remain situations where humans learn better or faster. With regard to classification of images, we argue that some of those situations are because the human visual system represents information in a format that promotes good training and classification. To demonstrate this idea, we show how occluding objects can impair performance of a deep learning system that is trained to classify digits in the MNIST database. We describe a human inspired segmentation and interpolation algorithm that attempts to reconstruct occluded parts of an image, and we show that using this reconstruction algorithm to pre-process occluded images promotes training and classification performance.

Authors

  • Michael Stettler
    École Polytechnique Fédérale de Lausanne (EPFL), Switzerland; Purdue University, Department of Psychological Sciences, 703 Third Street, West Lafayette, IN 47906, United States.
  • Gregory Francis
    École Polytechnique Fédérale de Lausanne (EPFL), Switzerland; Purdue University, Department of Psychological Sciences, 703 Third Street, West Lafayette, IN 47906, United States. Electronic address: gfrancis@purdue.edu.