Melih Kandemir


 I am an assistant professor at Özyeğin University,
Computer Science Department. My  research activity focuses primarily  on  development  of novel Bayesian inference  techniques  for  deep  learning and their  applications to computer  vision,  time series  analysis, and medical image analysis  problems.

name [dot] surname [at] ozyegin [dot] edu [dot] tr
Address: Nişantepe mah. Orman sok. 34-36, Alemdağ, Çekmeköy, İstanbul
Office: EF 104 | Phone: +90-216-564-9537
Scholar | GitHub | LinkedIn

MSc/PhD positions available! If you are interested in discovering new facts about probabilistic deep learning together with me and starting to publish scientific papers very early in your career, please email me your resume.


Selected Recent Work

(Full list available here)

  • Variational Bayesian multiple instance learning with Gaussian processes
    M. Haußmann, F.A. Hamprecht, M. Kandemir
    CVPR, (2017),  [PDF]
  • Variational weakly supervised Gaussian processes
    M. Kandemir, M. Haußmann, F. Diego, K. Rajamani, J. van der Laak, F.A. Hamprecht
    BMVC, Proceedings, (2016), (Oral) [PDF] [Code]
  • Gaussian process density counting from weak supervision
    M. von Borstel, M. Kandemir, P. Schmidt, M. Rao, K. Rajamani, F.A. Hamprecht
    ECCV, Proceedings, (2016) [PDF]
  • Asymmetric transfer learning with deep Gaussian processes
    M. Kandemir
    ICML, Proceedings, (2015) [PDF] [Code][Talk]
  • Instance label prediction by Dirichlet process multiple instance learning
    M. Kandemir, F.A. Hamprecht
    UAI, Proceedings, (2014) [PDF] [Code]