Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

Feb 11, 2021
Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool

* Paper and supplementary - Code: https://github.com/wvangansbeke/Unsupervised-Semantic-Segmentation 

  Access Paper or Ask Questions

Automated Search for Resource-Efficient Branched Multi-Task Networks

Aug 24, 2020
David Bruggemann, Menelaos Kanakis, Stamatios Georgoulis, Luc Van Gool

* British Machine Vision Conference (BMVC) 2020 

  Access Paper or Ask Questions

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference

Jul 24, 2020
Menelaos Kanakis, David Bruggemann, Suman Saha, Stamatios Georgoulis, Anton Obukhov, Luc Van Gool

* European Conference on Computer Vision (ECCV), 2020 

  Access Paper or Ask Questions

T-Basis: a Compact Representation for Neural Networks

Jul 13, 2020
Anton Obukhov, Maxim Rakhuba, Stamatios Georgoulis, Menelaos Kanakis, Dengxin Dai, Luc Van Gool

* Accepted at ICML 2020 

  Access Paper or Ask Questions

Learning To Classify Images Without Labels

May 25, 2020
Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool

* Paper + supplementary. Code + pretrained models: https://github.com/wvangansbeke/Unsupervised-Classification 

  Access Paper or Ask Questions

Revisiting Multi-Task Learning in the Deep Learning Era

Apr 28, 2020
Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Dengxin Dai, Luc Van Gool

* A survey on recent multi-task learning techniques 

  Access Paper or Ask Questions

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

Jan 19, 2020
Simon Vandenhende, Stamatios Georgoulis, Luc Van Gool


  Access Paper or Ask Questions

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

Dec 15, 2019
Suman Saha, Wenhao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yuhua Chen, Danda Pani Paudel, Luc Van Gool


  Access Paper or Ask Questions

Gated CRF Loss for Weakly Supervised Semantic Image Segmentation

Jun 11, 2019
Anton Obukhov, Stamatios Georgoulis, Dengxin Dai, Luc Van Gool

* 14 pages, 5 figures, 5 tables 

  Access Paper or Ask Questions

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

Oct 13, 2018
Liqian Ma, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc Van Gool


  Access Paper or Ask Questions

Disentangled Person Image Generation

Jun 15, 2018
Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, Mario Fritz

* Published at CVPR'18 (Spotlight). Corresponding author is Qianru Sun 

  Access Paper or Ask Questions

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

Feb 15, 2018
Davy Neven, Bert De Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool


  Access Paper or Ask Questions

Error Correction for Dense Semantic Image Labeling

Dec 11, 2017
Yu-Hui Huang, Xu Jia, Stamatios Georgoulis, Tinne Tuytelaars, Luc Van Gool


  Access Paper or Ask Questions

Fast Scene Understanding for Autonomous Driving

Aug 08, 2017
Davy Neven, Bert De Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool

* Published at "Deep Learning for Vehicle Perception", workshop at the IEEE Symposium on Intelligent Vehicles 2017 

  Access Paper or Ask Questions

What Is Around The Camera?

Aug 01, 2017
Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars, Luc Van Gool

* Accepted to ICCV. Project: http://homes.esat.kuleuven.be/~sgeorgou/multinatillum/ 

  Access Paper or Ask Questions

DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination

Mar 27, 2016
Stamatios Georgoulis, Konstantinos Rematas, Tobias Ritschel, Mario Fritz, Luc Van Gool, Tinne Tuytelaars

* Stamatios Georgoulis and Konstantinos Rematas contributed equally to this work 

  Access Paper or Ask Questions