Skip to main content
. Author manuscript; available in PMC: 2023 Feb 24.
Published in final edited form as: IEEE Trans Big Data. 2016 May 30;6(2):322–333. doi: 10.1109/tbdata.2016.2573280

Fig. 7.

Fig. 7.

Performance comparison of different methods. “SC” and “TL” denote sparse coding and transfer learning, respectively. “CTL + MTL” and “PTL + MTL” denote the performance achieved by complete and partial transfer learning, respectively, with multi-task learning models. We only consider the features extracted from layer 21 of these two deep models.