Skip to main content
. Author manuscript; available in PMC: 2020 Jan 9.
Published in final edited form as: IEEE Access. 2019 Jan 9;7:11093–11104. doi: 10.1109/ACCESS.2019.2891970

Fig. 8.

Fig. 8.

SVHN results for 500 and 1000 labeled samples in the training set, compared with semi-supervised learning with Deep generative network (DGN) [46], Skip Deep Generative Model [47], Improved GAN [44], Mutual exclusivity [10], Learning by association [16], the model [11] and the VAT model [13]. The best results in each column are shown in bold text.