September 24 – 29 , 2017, Dagstuhl Seminar 17391

Deep Learning for Computer Vision


Daniel Cremers (TU München, DE)
Laura Leal-Taixé (TU München, DE)
Ian Reid (University of Adelaide, AU)
René Vidal (Johns Hopkins University – Baltimore, US)

For support, please contact

Dagstuhl Service Team


Dagstuhl Report, Volume 7, Issue 9 Dagstuhl Report
Aims & Scope
List of Participants


The paradigm that a machine can learn from examples much like humans learn from experience has fascinated researchers since the advent of computers. It has triggered numerous research developments and gave rise to the concept of artificial neural networks as a computational paradigm designed to mimic aspects of signal and information processing in the human brain.

There have been several key advances in this area including the concept of back- propagation learning (essentially gradient descent and chain rule differentiation on the network weight vectors) by Werbos in 1974, later popularized in the celebrated 1984 paper of Rumelhart, Hinton and Williams. Despite a certain success in pattern recognition challenges like handwritten digit classification, artificial neural networks dropped in popularity in the 1990s with alternative techniques such as support vector machines gaining attention.

With increasing computational power (and in particular highly parallel GPU architectures) and more sophisticated training strategies such as layer-by-layer pretraining, supervised backpropagation and dropout learning, neural networks regained popularity in the 2000s and the 2010s. With deeper network architectures and more training data, their performance has drastically improved. Over the last couple of years, they have outperformed numerous existing algorithms on a variety of computer vision challenges such as object recognition, semantic segmentation and even stereo and optical flow estimation.

The aim of this Dagstuhl Seminar is to bring together leading experts from the area of machine learning and computer vision and discuss the state-of-the-art in deep learning for computer vision. During our seminar, we will address a variety of both experimental and theoretical questions such as:

  1. In which types of challenges do deep learning techniques work well?
  2. In which types of challenges do they fail? Are there variations of the network architectures that may enable us to tackle these challenges as well?
  3. Which type of network architectures exist (convolutional networks, recurrent networks, deep belief networks, long short-term memory networks, deep Turing machines)? What advantages and drawbacks does each network architecture bring about?
  4. Which aspects are crucial for the practical performance of deep network approaches?
  5. Which theoretical guarantees can be derived for neural network learning?
  6. What properties assure the impressive practical performance despite respective cost functions being generally non-convex?
Summary text license
  Creative Commons BY 3.0 Unported license
  Daniel Cremers, Laura Leal-Taixé, Ian Reid, and René Vidal


  • Artificial Intelligence / Robotics
  • Computer Graphics / Computer Vision


  • Deep learning
  • Convolutional networks
  • Computer vision
  • Machine learning


In the series Dagstuhl Reports each Dagstuhl Seminar and Dagstuhl Perspectives Workshop is documented. The seminar organizers, in cooperation with the collector, prepare a report that includes contributions from the participants' talks together with a summary of the seminar.


Download overview leaflet (PDF).

Dagstuhl's Impact

Please inform us when a publication was published as a result from your seminar. These publications are listed in the category Dagstuhl's Impact and are presented on a special shelf on the ground floor of the library.


Furthermore, a comprehensive peer-reviewed collection of research papers can be published in the series Dagstuhl Follow-Ups.