An Empirical Evaluation Study on the Training of SDC Features for Dense Pixel Matching
This work provides incremental insights into training deep neural networks for dense matching tasks, benefiting researchers in computer vision.
The study empirically evaluates training strategies for the SDC descriptor network, focusing on hyperparameter tuning, data selection, loss design, and schedules to optimize dense pixel matching performance.
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.