Persönlicher Status und Werkzeuge

Home Members Caner Hazırbaş

Caner Hazırbaş

Caner Hazırbaş

Scientific Employee

Technische Universität München

Department of Computer Science
Informatik 9
Boltzmannstrasse 3
85748 Garching

Tel: +49-89-289-17788
Fax: +49-89-289-17757
Office: 02.09.041

Research Interests

I am interested in Deep Learning, Object Recognition/Detection and Semantic Scene Understanding.

Wanna know more about deep learning? Here is a short intro to the topic:

Google Scholar : h-index: 4, citations: 203

I recommend all students who consider doing a phd to read the PhD Grind book.

Brief Bio

I received my Bachelor's Degree with honor in Computer Engineering from Yildiz Technical University, Istanbul (2011) and Master's Degree with distinction in Informatics from the Technical University, Munich (2014).

Since August 2014, I am a PhD student in the Computer Vision Research Group, headed by Prof. Dr. Daniel Cremers at the Technical University, Munich.

I attended Machine Learning Summer School 2015 Kyoto (MLSS'2015 Kyoto) in Japan. Please visit here to access my daily blog for the summer school.

My personal webpage:

My social profiles: Linkedin GitHub Google+ YouTube


Conference and Workshop Papers
Deep Depth From Focus (Caner Hazirbas, Laura Leal-Taixé, Daniel Cremers), In ArXiv preprint arXiv:1704.01085, 2017. ([arxiv]) [bib]
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems (Tim Meinhardt, Michael Möller, Caner Hazirbas, Daniel Cremers), In ArXiv preprint arXiv:1704.03488, 2017. ([arxiv]) [bib]
Image-based localization using LSTMs for structured feature correlation (Florian Walch, Caner Hazirbas, Laura Leal-Taixé, Torsten Sattler, Sebastian Hilsenbeck, Daniel Cremers), In ArXiv preprint 1611.07890, 2016. ([arxiv]) [bib]
FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture (C. Hazirbas, L. Ma, C. Domokos, D. Cremers), In Asian Conference on Computer Vision, 2016. ([code]) [bib] [pdf]
CAPTCHA Recognition with Active Deep Learning (F. Stark, C. Hazirbas, R. Triebel, D. Cremers), In GCPR Workshop on New Challenges in Neural Computation, 2015. ([code]) [bib] [pdf]
FlowNet: Learning Optical Flow with Convolutional Networks (A. Dosovitskiy, P. Fischer, E. Ilg, P. Haeusser, C. Hazirbas, V. Golkov, P. van der Smagt, D. Cremers, T. Brox), In IEEE International Conference on Computer Vision (ICCV), 2015. ([video],[code]) [bib] [pdf] [doi]
Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation (C. Hazirbas, J. Diebold, D. Cremers), In Scale Space and Variational Methods in Computer Vision (SSVM), 2015. ([code]) [bib] [pdf] [doi]Oral Presentation
Interactive Multi-label Segmentation of RGB-D Images (J. Diebold, N. Demmel, C. Hazirbas, M. Möller, D. Cremers), In Scale Space and Variational Methods in Computer Vision (SSVM), 2015. ([code]) [bib] [pdf] [doi]
Masters Thesis
Feature Selection and Learning for Semantic Segmentation (Caner Hazirbas), Master's thesis, Technical University Munich, 2014. [bib] [pdf]
Powered by bibtexbrowser
Export as PDF or BIB

Project Supervision

Please send me an e-mail or drop by my office if you would like to work on an IDP, Guided Research or Master's Thesis with me. You are required to know basic programming skills (C++/Python) and to have a strong background in math and deep learning. Some experience in TensorFlow is preferred. Do not hesitate to contact me for any kind of research discussion. We DO NOT offer internships.

Project topics, I am currently working on, listed below:

  • Depth From Focus (DFF)
    • Light field imaging
    • Deep Networks for DFF
  • Image Localization
    • Deep CNNs and LSTMs for image-based localization
  • Scribble-based RGB-D Image Segmentation
    • RGB-D image segmentation based on scribbles with deep CNNs
  • Scene Understanding with Deep Convolutional Neural Networks
    • Large scale object recognition/detection
    • Scene recognition
    • Multiclass image segmentation
Last edited 06.04.2017 10:15 by Caner Hazirbas