Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly

Yongqin Xian , Christoph H. LampertBernt SchieleZeynep Akata

 

Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. 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 of publicly available datasets used for this task. 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. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. 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 in detail the limitations of the current status of the area which can be taken as a basis for advancing it. 

[News]: We introduce Proposed Splits Version 2.0 which fixed an issue in the original Proposed Split. We did not observe significant performance difference between the original Proposed Splits and Proposed Splits Version 2.0. More details can be found in this report. Please download Proposed Splits Version 2.0 below.

Paper

Data Splits and Features for CUB, AWA1, AWA2, SUN and APY

Data Splits and Features for ImageNet

 

If you find it useful, please cite:

 

@inproceedings {xianCVPR17, 	
 title = {Zero-Shot Learning - The Good, the Bad and the Ugly}, 	
 booktitle = {IEEE Computer Vision and Pattern Recognition (CVPR)}, 	
 year = {2017}, 	
 author = {Yongqin Xian and Bernt Schiele and Zeynep Akata} 
} 

 

@article{XLSA18,
 title={Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly},
 author={Xian, Yongqin and Lampert, H. Christoph and Schiele, Bernt and Akata, Zeynep},
 journal={TPAMI},
 year={2018},
}