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

Gabriel Eilertsen

Ensembles of GANs for synthetic training data generation


Apr 23, 2021
Gabriel Eilertsen, Apostolia Tsirikoglou, Claes Lundström, Jonas Unger

Figure 1 for Ensembles of GANs for synthetic training data generation
Figure 2 for Ensembles of GANs for synthetic training data generation
Figure 3 for Ensembles of GANs for synthetic training data generation
Figure 4 for Ensembles of GANs for synthetic training data generation
* 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 Pocevičiūtė, Gabriel Eilertsen, Claes Lundström

Figure 1 for Unsupervised anomaly detection in digital pathology using GANs
Figure 2 for Unsupervised anomaly detection in digital pathology using GANs
Figure 3 for Unsupervised anomaly detection in digital pathology using GANs
Figure 4 for Unsupervised anomaly detection in digital pathology using GANs

  Access Paper or Ask Questions

Survey of XAI in digital pathology


Aug 14, 2020
Milda Pocevičiūtė, Gabriel Eilertsen, Claes Lundström

Figure 1 for Survey of XAI in digital pathology
Figure 2 for Survey of XAI in digital pathology
Figure 3 for Survey of XAI in digital pathology
Figure 4 for Survey of XAI in digital pathology

  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

Figure 1 for A Study of Deep Learning Colon Cancer Detection in Limited Data Access Scenarios
* 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 Jönsson, Timo Ropinski, Jonas Unger, Anders Ynnerman

Figure 1 for Classifying the classifier: dissecting the weight space of neural networks
Figure 2 for Classifying the classifier: dissecting the weight space of neural networks
Figure 3 for Classifying the classifier: dissecting the weight space of neural networks
Figure 4 for Classifying the classifier: dissecting the weight space of neural networks
* 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 Lundström

Figure 1 for A Closer Look at Domain Shift for Deep Learning in Histopathology
Figure 2 for A Closer Look at Domain Shift for Deep Learning in Histopathology
Figure 3 for A Closer Look at Domain Shift for Deep Learning in Histopathology
Figure 4 for A Closer Look at Domain Shift for Deep Learning in Histopathology
* 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

Figure 1 for Single-frame Regularization for Temporally Stable CNNs
Figure 2 for Single-frame Regularization for Temporally Stable CNNs
Figure 3 for Single-frame Regularization for Temporally Stable CNNs
Figure 4 for Single-frame Regularization for Temporally Stable CNNs
* 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

Figure 1 for HDR image reconstruction from a single exposure using deep CNNs
Figure 2 for HDR image reconstruction from a single exposure using deep CNNs
Figure 3 for HDR image reconstruction from a single exposure using deep CNNs
Figure 4 for HDR image reconstruction from a single exposure using deep CNNs
* ACM Trans. Graph. 36, 6, Article 178 (2017) 
 * 15 pages, 19 figures, Siggraph Asia 2017. Project webpage located at http://hdrv.org/hdrcnn/ where paper with high quality images is available, as well as supplementary material (document, images, video and source code) 
  Access Paper or Ask Questions