Search Results for author: Jonas Unger

Found 15 papers, 7 papers with code

Comparison of single image HDR reconstruction methods — the caveats of quality assessment

1 code implementation ACM SIGGRAPH Conference Proceedings 2022 Param Hanji, Rafał K. Mantiuk, Gabriel Eilertsen, Saghi Hajisharif, Jonas Unger

As the problem of reconstructing high dynamic range (HDR) images from a single exposure has attracted much research effort, it is essential to provide a robust protocol and clear guidelines on how to evaluate and compare new methods.

HDR Reconstruction

Standalone Neural ODEs with Sensitivity Analysis

no code implementations27 May 2022 Rym Jaroudi, Lukáš Malý, Gabriel Eilertsen, B. Tomas Johansson, Jonas Unger, George Baravdish

This paper presents the Standalone Neural ODE (sNODE), a continuous-depth neural ODE model capable of describing a full deep neural network.

Learning via nonlinear conjugate gradients and depth-varying neural ODEs

no code implementations11 Feb 2022 George Baravdish, Gabriel Eilertsen, Rym Jaroudi, B. Tomas Johansson, Lukáš Malý, Jonas Unger

The inverse problem of supervised reconstruction of depth-variable (time-dependent) parameters in a neural ordinary differential equation (NODE) is considered, that means finding the weights of a residual network with time continuous layers.

Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications

1 code implementation10 Dec 2021 Karin Stacke, Jonas Unger, Claes Lundström, Gabriel Eilertsen

We bring forward a number of considerations, such as view generation for the contrastive objective and hyper-parameter tuning.

Benchmarking Contrastive Learning +1

Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node Colon Adenocarcinoma Metastasis Detection

no code implementations17 Sep 2021 Apostolia Tsirikoglou, Karin Stacke, Gabriel Eilertsen, Jonas Unger

The scarcity of labeled data is a major bottleneck for developing accurate and robust deep learning-based models for histopathology applications.

Data Augmentation

How to cheat with metrics in single-image HDR reconstruction

1 code implementation19 Aug 2021 Gabriel Eilertsen, Saghi Hajisharif, Param Hanji, Apostolia Tsirikoglou, Rafal K. Mantiuk, Jonas Unger

Here, we reproduce a typical evaluation using existing as well as simulated SI-HDR methods to demonstrate how different aspects of the problem affect objective quality metrics.

HDR Reconstruction

Ensembles of GANs for synthetic training data generation

no code implementations23 Apr 2021 Gabriel Eilertsen, Apostolia Tsirikoglou, Claes Lundström, Jonas Unger

This work investigates the use of synthetic images, created by generative adversarial networks (GANs), as the only source of training data.


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

no code implementations20 May 2020 Apostolia Tsirikoglou, Karin Stacke, Gabriel Eilertsen, Martin Lindvall, Jonas Unger

One such scenario relates to detecting tumor metastasis in lymph node tissue, where the low ratio of tumor to non-tumor cells makes the diagnostic task hard and time-consuming.

Classifying the classifier: dissecting the weight space of neural networks

1 code implementation13 Feb 2020 Gabriel Eilertsen, Daniel Jönsson, Timo Ropinski, Jonas Unger, Anders Ynnerman

of neural network classifiers, and train a large number of models to represent the weight space.

A Closer Look at Domain Shift for Deep Learning in Histopathology

1 code implementation25 Sep 2019 Karin Stacke, Gabriel Eilertsen, Jonas Unger, Claes Lundström

Most centrally, we present a novel measure for evaluating the distance between domains in the context of the learned representation of a particular model.

General Classification whole slide images

Single-frame Regularization for Temporally Stable CNNs

no code implementations CVPR 2019 Gabriel Eilertsen, Rafał K. Mantiuk, Jonas Unger

The regularization is formulated to account for different types of motion that can occur between frames, so that temporally stable CNNs can be trained without the need for video material or expensive motion estimation.

Motion Estimation Optical Flow Estimation

Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing

2 code implementations19 Oct 2018 Magnus Wrenninge, Jonas Unger

We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis.

Street Scene Parsing

HDR image reconstruction from a single exposure using deep CNNs

2 code implementations20 Oct 2017 Gabriel Eilertsen, Joel Kronander, Gyorgy Denes, Rafał K. Mantiuk, Jonas Unger

We demonstrate that our approach can reconstruct high-resolution visually convincing HDR results in a wide range of situations, and that it generalizes well to reconstruction of images captured with arbitrary and low-end cameras that use unknown camera response functions and post-processing.

HDR Reconstruction Image Reconstruction +1

Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications

no code implementations17 Oct 2017 Apostolia Tsirikoglou, Joel Kronander, Magnus Wrenninge, Jonas Unger

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vision tasks.

Autonomous Vehicles Image Generation +2

A Unified Framework for Multi-Sensor HDR Video Reconstruction

no code implementations22 Aug 2013 Joel Kronander, Stefan Gustavson, Gerhard Bonnet, Anders Ynnerman, Jonas Unger

We present an implementation in CUDA and show real-time performance for an experimental 4 Mpixel multi-sensor HDR video system.

Denoising HDR Reconstruction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.