Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes) by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impacts on the ZSL system performance. This letter first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting the subset of key attributes can improve the generalization performance of the original ZSL model, which uses all the attributes. Unfortunately, previous attribute selection methods have been conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks. Inspired by learning from pseudo-relevance feedback, this letter introduces out-of-the-box data—pseudo-data generated by an attribute-guided generative model—to mimic the unseen data. We then present an iterative attribute selection (IAS) strategy that iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to that of the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance.