no code implementations • 16 Oct 2018 • Zi-Yi Ke, Chiou-Ting Hsu
Finally, we derive pseudo pixel-level labels from these localization maps and use the pseudo labels as ground truth to train the semantic segmentation model.
no code implementations • 11 Apr 2014 • Kazuyuki Tanaka, Shun Kataoka, Muneki Yasuda, Yuji Waizumi, Chiou-Ting Hsu
This paper presents a Bayesian image segmentation model based on Potts prior and loopy belief propagation.