Persistent Evidence of Local Image Properties in Generic ConvNets

  • Ali Sharif Razavian
  • Hossein Azizpour
  • Atsuto Maki
  • Josephine Sullivan
  • Carl Henrik Ek
  • Stefan Carlsson
Conference paper

DOI: 10.1007/978-3-319-19665-7_21

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9127)
Cite this paper as:
Razavian A.S., Azizpour H., Maki A., Sullivan J., Ek C.H., Carlsson S. (2015) Persistent Evidence of Local Image Properties in Generic ConvNets. In: Paulsen R., Pedersen K. (eds) Image Analysis. SCIA 2015. Lecture Notes in Computer Science, vol 9127. Springer, Cham

Abstract

Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or the variation within the object class. Does this happen in practice? Although this seems to pertain to the very final layers in the network, if we look at earlier layers we find that this is not the case. In fact, strong spatial information is implicit. This paper addresses this, in particular, exploiting the image representation at the first fully connected layer, i.e. the global image descriptor which has been recently shown to be most effective in a range of visual recognition tasks. We empirically demonstrate evidences for the finding in the contexts of four different tasks: 2d landmark detection, 2d object keypoints prediction, estimation of the RGB values of input image, and recovery of semantic label of each pixel. We base our investigation on a simple framework with ridge rigression commonly across these tasks, and show results which all support our insight. Such spatial information can be used for computing correspondence of landmarks to a good accuracy, but should potentially be useful for improving the training of the convolutional nets for classification purposes.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Ali Sharif Razavian
    • 1
  • Hossein Azizpour
    • 1
  • Atsuto Maki
    • 1
  • Josephine Sullivan
    • 1
  • Carl Henrik Ek
    • 1
  • Stefan Carlsson
    • 1
  1. 1.Computer Vision and Active Perception Lab (CVAP), School of Computer Science and Communication (CSC)Royal Institute of Technology (KTH)StockholmSweden

Personalised recommendations