On Pre-Trained Image Features and Synthetic Images for Deep Learning
ECCV Workshops, pp. 682-697, 2018.
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
PPT (Upload PPT)