Supplementary Material: Synthesized Classifiers for Zero-Shot Learning

There are a few free hyper-parameters in our approach (cf. Section 3.2 of the main text). To choose the hyper-parameters in the conventional cross-validation (CV) for multi-way classification, one splits the training data into several folds such that they share the same set of class labels with one another. Clearly, this strategy is not sensible for zero-shot learning as it does not imitate what actually happens at the test stage. We thus introduce a new strategy for performing CV, inspired by the hyper-parameter tuning in [25]. The key difference of the new scheme to the conventional CV is that we split the data into several folds such that the class labels of these folds are disjoint. For clarity, we denote the conventional CV as sample-wise CV and our scheme as class-wise CV. Figure 1(b) and 1(c) illustrate the two scenarios, respectively. We empirically compare them in Section 5.1. Note that several existing models [2, 7, 25, 34] also follow similar hyper-prameter tuning procedures.