2022/04/08 by Rodner, Erik, Denzler, Joachim
#Object detection #knowledge transfer #one-shot learning
paper · doi:10.4230/dagsemproc.08422.9
Visual object localization and categorization is still a big challenge for current research and gets even more difficult when confronted with few training examples. Therefore we will present a Bayesian concept to enhance state-of-the-art machine learning techniques even when dealing with just a single view of an object category. Furthermore an object localization approach is presented, which can serve as a baseline for researchers within the area of object localization.