Skip to main content
. Author manuscript; available in PMC: 2020 Mar 26.
Published in final edited form as: Proc IEEE Int Conf Comput Vis. 2020 Feb 27;2019:2580–2590. doi: 10.1109/iccv.2019.00267

Figure 9.

Figure 9.

Our method’s improvement over transfer learning (in terms of R@100 for predicate classification) is correlated to the number of subtypes in the train set (left), the number of subtypes in the unlabeled set (middle), and the proportion of subtypes in the labeled set (right).