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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Gabriel Eilertsen

Ensembles of GANs for synthetic training data generation

Apr 23, 2021
Gabriel Eilertsen, Apostolia Tsirikoglou, Claes Lundstr├Âm, Jonas Unger

* ICLR 2021 workshop on Synthetic Data Generation: Quality, Privacy, Bias 

  Access Paper or Ask Questions

Unsupervised anomaly detection in digital pathology using GANs

Mar 16, 2021
Milda Pocevi─Źi┼źt─Ś, Gabriel Eilertsen, Claes Lundstr├Âm

  Access Paper or Ask Questions

Survey of XAI in digital pathology

Aug 14, 2020
Milda Pocevi─Źi┼źt─Ś, Gabriel Eilertsen, Claes Lundstr├Âm

  Access Paper or Ask Questions

A Study of Deep Learning Colon Cancer Detection in Limited Data Access Scenarios

May 22, 2020
Apostolia Tsirikoglou, Karin Stacke, Gabriel Eilertsen, Martin Lindvall, Jonas Unger

* Presented at the ICLR 2020 Workshop on AI for Overcoming Global Disparities in Cancer Care (AI4CC) 

  Access Paper or Ask Questions

Classifying the classifier: dissecting the weight space of neural networks

Feb 13, 2020
Gabriel Eilertsen, Daniel J├Ânsson, Timo Ropinski, Jonas Unger, Anders Ynnerman

* ECAI 2020 

  Access Paper or Ask Questions

A Closer Look at Domain Shift for Deep Learning in Histopathology

Sep 26, 2019
Karin Stacke, Gabriel Eilertsen, Jonas Unger, Claes Lundstr├Âm

* 8 pages, 4 figures. Accepted to COMPAY2019: Second MICCAI Workshop on Computational Pathology 

  Access Paper or Ask Questions

Single-frame Regularization for Temporally Stable CNNs

Feb 27, 2019
Gabriel Eilertsen, Rafał K. Mantiuk, Jonas Unger

* CVPR 2019 

  Access Paper or Ask Questions

HDR image reconstruction from a single exposure using deep CNNs

Oct 20, 2017
Gabriel Eilertsen, Joel Kronander, Gyorgy Denes, Rafał K. Mantiuk, Jonas Unger

* ACM Trans. Graph. 36, 6, Article 178 (2017) 
* 15 pages, 19 figures, Siggraph Asia 2017. Project webpage located at where paper with high quality images is available, as well as supplementary material (document, images, video and source code) 

  Access Paper or Ask Questions