Authors:
Amin Dadgar
and
Guido Brunnett
Affiliation:
Computer Science, Chemnitz University of Technology, Straße der Nationen 62, 09111, Chemnitz, Germany
Keyword(s):
Machine Learning, Neural Networks, Deep Learning, Segmentation, Synthetic Training Set, Transfer Learning, Learning Saturation, Premature Learning Saturation, Repetitive Training.
Abstract:
We propose an approach to segment hands in real scenes. To that, we employ 1) a relatively large amount of sorely simplistic synthetic images, 2) a small number of real images, and propose 3) a training scheme of repetitive training to resolve the phenomenon we call premature learning saturation (for using relatively large training set). The results suggest the feasibility of hand segmentation subject to attending to the parameters and specifications of each category with meticulous care. We conduct a short study to quantitatively demonstrate the benefits of our repetitive training on a more general ground with the Mask-RCNN framework.