Stamatios Georgoulis - PostDoc, ETH Zurich

Stamatios

Georgoulis

PostDoc @ ETH Zurich

Computer Vision and Machine Learning

About Me

Hey there! I am Stamatios Georgoulis, although most people know me as 'Stam', and I come from a small but beautiful island in the Aegean Sea, called Sifnos. Currently, I am a 3^rd-year post-doctoral researcher at the CVL group of ETH Zurich, working with Prof. Luc Van Gool. I am fascinated by many research topics, by you will usually find me publishing image generation, dense prediction, and multi-task learning papers.

Before coming to Zurich, I was a doctoral student at the PSI-VISICS group of KU Leuven. There, I received my PhD under the supervision of Prof. Luc Van Gool and Prof. Tinne Tuytelaars, and I also had the pleasure to collaborate with Prof. Mario Fritz, Prof. Tobias Ritschel and Dr. Konstantinos Rematas. During my PhD, my research was mainly focused on extracting surface characteristics and lighting - in particular, 3D shape, surface reflectance, and environmental illumination - from images.

Further back, before even arriving in Leuven, I received my diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki. I conducted the research for my diploma thesis on "Adaptive Pain Detection via Webcam using Advanced Image Processing Techniques" in collaboration with Dr. Stefanos Eleftheriadis under the supervision of Prof. Leontios Hadjileontiadis. During my stay in Thessaloniki, I worked as a student research assistant in the Signal Processing and Biomedical Technology Unit.

News

23.01.2021

Our survey paper on multi-tasking learning was accepted for publication at the TPAMI journal, and our paper on spectral tensor train parameterization was accepted for publication at the AISTATS 2021 conference.

05.08.2020

Two papers on multi-task learning were accepted for publication at the BMVC 2020 conference

02.07.2020

Two papers on multi-task learning and one on unsupervised clustering were accepted for publication at the ECCV 2020 conference

01.07.2020

In conjunction with my postdoc role at ETH Zurich, I started a part-time role as a Computer Vision and Machine Learning researcher at Huawei's Zurich Research Center

19.06.2020

Our paper on domain adaptation for face anti-spoofing won best paper award at the IEEE Computer Society Biometrics Workshop of the CVPR 2020 conference

Selected Publications

2021

Multi-Task Learning for Dense Prediction Tasks: A Survey

S. Vandenhende, S. Georgoulis, W. Van Gansbeke, M. Proesmans, D. Dai, L. Van Gool
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
2021
ArXiv | BibTex

2020

Automated Search for Resource-Efficient Branched Multi-Task Networks

D. Bruggemann, M. Kanakis, S. Georgoulis, and L. Van Gool
In British Machine Vision Conference (BMVC'20)
Virtual Conference, September 7-10, 2020
ArXiv | BibTex

Branched Multi-Task Networks: Deciding What Layers To Share

S. Vandenhende, S. Georgoulis, B. De Brabandere and L. Van Gool
In British Machine Vision Conference (BMVC'20)
Virtual Conference, September 7-10, 2020
ArXiv | BibTex

SCAN: Learning to Classify Images without Labels

W. Van Gansbeke*, S. Vandenhende*, S. Georgoulis, M. Proesmans and L. Van Gool
*denotes equal contribution
In European Conference on Computer Vision (ECCV'20)
Virtual Conference, August 23-28, 2020
ArXiv | BibTex | Code

MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning

S. Vandenhende, S. Georgoulis and L. Van Gool
In European Conference on Computer Vision (ECCV'20)
Virtual Conference, August 23-28, 2020
ArXiv | BibTex | Code

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference

M. Kanakis, D. Bruggemann, S. Saha, S. Georgoulis, A. Obukhov and L. Van Gool
In European Conference on Computer Vision (ECCV'20)
Virtual Conference, August 23-28, 2020
ArXiv | BibTex | Code

T-Basis: a Compact Representation for Neural Networks

A. Obukhov, M. Rakhuba, S. Georgoulis, M. Kanakis, D. Dai and L. Van Gool
In International Conference on Machine Learning (ICML'20)
Virtual Conference, July 13-18, 2020
ArXiv | BibTex

Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing

S. Saha, W. Xu, M. Kanakis, S. Georgoulis, Y. Chen, D. P. Paudel and L. Van Gool
In Computer Vision and Pattern Recognition Workshops (CVPR-W'20)
Virtual Conference, June 14-19, 2020
ArXiv | BibTex

2019

Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

L. Ma, X. Jia, S. Georgoulis, T. Tuytelaars and L. Van Gool
In International Conference on Learning Representations (ICLR'19)
New Orleans, Louisiana, USA, May 6-9, 2019
OpenReview | BibTex

2018

Towards End-to-End Lane Detection: an Instance Segmentation Approach

D. Neven, B. De Brabandere, S. Georgoulis, M. Proesmans and L. Van Gool
In IEEE Intelligent Vehicles Symposium (IV'18)
Changshu, Suzhou, China, June 26-30, 2018
PDF | BibTex

Disentangled Person Image Generation

L. Ma, Q. Sun, S. Georgoulis, L. Van Gool, B. Schiele and M. Fritz
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'18, spotlight)
Salt Lake City, Utah, USA, June 18-22, 2018
PDF | BibTex | Project | Code

2017

What Is Around The Camera?

S. Georgoulis, K. Rematas, T. Ritschel, M. Fritz, T. Tuytelaars and L. Van Gool
In IEEE International Conference on Computer Vision (ICCV'17)
Venice, Italy, October 22-29, 2017
PDF | BibTex | Project | Dataset & Code

Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning

S. Georgoulis*, K. Rematas*, T. Ritschel, E. Gavves, M. Fritz, L. Van Gool and T. Tuytelaars
*denotes equal contribution
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
2017
DOI | BibTex | Project & Code

Fast Scene Understanding for Autonomous Driving

D. Neven, B. De Brabandere, S. Georgoulis, M. Proesmans and L. Van Gool
In IEEE Intelligent Vehicles Symposium Workshops (IV-W'17)
Redondo Beach, CA, USA, June 11-14, 2017
PDF | BibTex | Video | Code

2015

A Gaussian Process Latent Variable Model for BRDF Inference

S. Georgoulis, V. Vanweddingen, M. Proesmans and L. Van Gool
In IEEE International Conference on Computer Vision (ICCV'15)
Santiago, Chile, December 13-16, 2015
DOI | BibTex | Video | Code

Reviewing

CVPR 2021 (reviewer), ECCV 2020 (reviewer), BMVC 2020 (reviewer), CVPR 2020 (reviewer), NeurIPS 2019 (top 50% reviewer), ICCV 2019 (outstanding reviewer), CVPR 2019 (reviewer), NIPS 2018 (outstanding reviewer), SIGGRAPH Asia 2018 (emergency reviewer), CVPR 2018 (reviewer), ICRA 2018 (emergency reviewer), NIPS 2017 (reviewer).

Contact

[firstname] [dot] [lastname] [at]
vision [dot] ee [dot] ethz [dot] ch

Computer Vision Laboratory
Sternwartstrasse 7
ETH Zentrum
CH - 8092 Zurich, Switzerland

office: ETF D113.2
tel. +41 44 63 27663