“…For comparison, we evaluate the fore-and background segmentation performances by some existing models that employ RBM, such as GLOC (Kae et al 2013), CHOPPS (Li, Tarlow, and Zemel 2013) and MMBM (Yang, Safar, and Yang 2014), and DeepLab (Chen et al 2016). We also tested the framework Fig.3 implemented with a standard CNN encoder (and the classification layer), as the baseline model, following (Sabour, Frosst, and Hinton 2017).…”