Prof. Dr. Didier Stricker
Dr. Alain Pagani
Dr. Gerd Reis
M.A. Eric Thil
Nicole Stephanie Buhlinger
Keonna Cunningham
Dr. Oliver Wasenmüller
Dr. Gabriele Bleser
Dr. Bertram Taetz
Sk Aziz Ali
Rashed Al Koutayni
Yuriy Anisimov
Jilliam Maria Diaz Barros
Ramy Battrawy
Hammad Butt
Mahdi Chamseddine
Steve Dias da Cruz
Fangwen Shu
Torben Fetzer
Michael Fürst
Christiano Couto Gava
Tewodros Amberbir Habtegebrial
Hartmut Feld
Jigyasa Katrolia
Andreas Kölsch
Onorina Kovalenko
Stephan Krauß
Paul Lesur
Muhammad Jameel Nawaz Malik
Mina Ameli
Nareg Minaskan Karabid
Pramod Murthy
Mathias Musahl
Peter Neigel
Manthan Pancholi
Jason Raphael Rambach
María Alejandra Sánchez Marín
Kripasindhu Sarkar
Alexander Schäfer
René Schuster
Mohamed Selim
Dennis Stumpf
Yongzhi Su
Xiaoying Tan
André Luiz Brandão
Ahmet Firintepe
Vladislav Golyanik
Aditya Tewari
An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
Conference on Computer Vision and Pattern Recognition Workshops. Safe Artificial Intelligence for Automated Driving Workshop (SAIAD-2019) befindet sich CVPR 2019 June 17-17 Long Beach CA United States IEEE Xplore 2019 .
- Abstract:
- Training a deep neural network is a non-trivial task. Not only the tuning of hyperparameters, but also the gathering and selection of training data, the design of the loss function, and the construction of training schedules is important to get the most out of a model. In this study, we perform a set of experiments all related to these issues. The model for which different training strategies are investigated is the recently presented SDC descriptor network (stacked dilated convolution). It is used to describe images on pixel-level for dense matching tasks. Our work analyzes SDC in more detail, validates some best practices for training deep neural networks, and provides insights into training with multiple domain data.