On Pre-Trained Image Features and Synthetic Images for Deep Learning

ECCV Workshops, pp. 682-697, 2018.

Cited by: 77|Bibtex|Views90|DOI:https://doi.org/10.1007/978-3-030-11009-3_42
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the labeling comes for free, and several approaches have been proposed to combine synthetic and real images f...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments