Zero-Shot Learning -- The Good, the Bad and the Ugly
This addresses the problem of inconsistent evaluation in zero-shot learning for researchers, though it is incremental as it builds on existing methods.
The paper tackles the lack of standardized benchmarks in zero-shot learning by defining a unified benchmark and evaluating state-of-the-art methods, revealing issues like flawed comparisons due to pre-training on test classes.
Due to the importance of zero-shot learning, the number of proposed approaches has increased steadily recently. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss limitations of the current status of the area which can be taken as a basis for advancing it.