Zero-Shot Learning — The Good, the Bad and the Ugly
Authors:
- Yongqin XianYXYongqin Xian
- Bernt SchieleBSBernt Schiele
- Zeynep AkataZAZeynep Akata
Top Cited Papers
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3077-3086
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 27 references indexed in Scilit:
- Deep Residual Learning for Image Recognition2016
- Semi-supervised Vocabulary-Informed Learning2016
- Latent Embeddings for Zero-Shot Classification2016
- Zero-shot object recognition by semantic manifold distance2015
- Going deeper with convolutions2015
- Toward Open Set RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Evaluating knowledge transfer and zero-shot learning in a large-scale setting2011
- Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example2010
- Ranking with ordered weighted pairwise classification2009
- Describing objects by their attributes2009