Postdoc in Computer Vision / Machine Learning / Applied Mathematics

Job description

The Division of Computational Science and Technology at KTH Royal Institute of Technology in Stockholm, Sweden is seeking a Postdoc in Computer Vision / Machine Learning / Applied Mathematics to handle scale-dependent image information in deep networks.

In our research, we develop deep networks for processing image data that handle scaling transformations and other image transformations in a theoretically well-founded manner. Our research in this area comprises both theoretical modelling of the influence of image transformations on different architectures for deep networks and the experimental evaluation of such networks on benchmark datasets to explore their properties. The work also comprises the creation of new benchmark datasets, to enable characterization of properties of deep networks that are not covered by existing datasets. For examples of our previous work in this area, see https://www.kth.se/profile/tony/page/deep-networks

Within the scope of this postdoc position, you are expected to work on and contribute to the research frontier regarding scale-covariant or scale-equivariant deep networks and/or deep networks parameterized in terms of Gaussian derivatives, on specific research topics that we choose together.

The selected candidate will work closely together with the project leader Tony Lindeberg.

Qualifications requirements

* A doctoral degree or an equivalent foreign degree, obtained within the last three years prior to the application deadline * We are seeking a candidate with a PhD in Computer Vision, Machine Learning, Applied Mathematics or a related discipline dealing with automated analysis of image information. * Previous experience with experimental evaluations using deep learning architectures applied to image data is necessary, preferably PyTorch. * A theoretical background in continuous mathematics for modelling convolutions and the influence of image transformations on image data is also necessary.

Preferred qualifications

As a person you have excellent scientific and collaborative skills, in combination with independence, with very good ability to get into new scientific theories and conduct implementations and experimental evaluations in close collaboration with the research environment you are working in.

The preferred candidates should have demonstrated expertise (through publications) in any one of the following:

* Deep networks that handle image information for computer vision tasks, including experimental evaluation using modern architectures for deep networks. * Continuous models for deep networks applied to image information. * Theoretical modelling of scaling transformations or other image transformations applied to automated processing of image information.

For further information and information about to how to apply, see https://www.kth.se/en/om/work-at-kth/lediga-jobb/what:job/jobID:490734/

Application deadline: May 2, 2022

The position is offered for a period of two years.

[cid:FD2B374F-C472-4895-ADA7-B3CD5419FD22@csc.kth.se]

Tony Lindeberg Professor of Computer Science — Computational Vision

KTH Royal Institute of Technology Computational Brain Science Lab Division of Computational Science and Technology, CST SE-100 44 Stockholm, Sweden

Phone: +46 8 790 6205 https://www.kth.se/profile/tony/