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
René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker
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.