Zero-Shot Learning -- The Good, the Bad and the Ugly
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- An Embarrassingly Simple Approach to Zero-Shot Learning2017
- An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild2016
- Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication2016
- Multi-class Open Set Recognition Using Probability of Inclusion2014
- Label-Embedding for Attribute-Based Classification2013
- SUN attribute database: Discovering, annotating, and recognizing scene attributes2012
- Evaluating knowledge transfer and zero-shot learning in a large-scale setting2011
- Large scale image annotation: learning to rank with joint word-image embeddingsMachine Learning, 2010
- What helps where – and why? Semantic relatedness for knowledge transfer2010
- Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example2010