Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?

Type
Conference Paper

Authors
Alabdulmohsin, Ibrahim
Cisse, Moustapha
Zhang, Xiangliang

KAUST Department
Computer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Online Publication Date
2016-09-04

Print Publication Date
2016

Date
2016-09-04

Abstract
One transfer learning approach that has gained a wide popularity lately is attribute-based zero-shot learning. Its goal is to learn novel classes that were never seen during the training stage. The classical route towards realizing this goal is to incorporate a prior knowledge, in the form of a semantic embedding of classes, and to learn to predict classes indirectly via their semantic attributes. Despite the amount of research devoted to this subject lately, no known algorithm has yet reported a predictive accuracy that could exceed the accuracy of supervised learning with very few training examples. For instance, the direct attribute prediction (DAP) algorithm, which forms a standard baseline for the task, is known to be as accurate as supervised learning when as few as two examples from each hidden class are used for training on some popular benchmark datasets! In this paper, we argue that this lack of significant results in the literature is not a coincidence; attribute-based zero-shot learning is fundamentally an ill-posed strategy. The key insight is the observation that the mechanical task of predicting an attribute is, in fact, quite different from the epistemological task of learning the “correct meaning” of the attribute itself. This renders attribute-based zero-shot learning fundamentally ill-posed. In more precise mathematical terms, attribute-based zero-shot learning is equivalent to the mirage goal of learning with respect to one distribution of instances, with the hope of being able to predict with respect to any arbitrary distribution. We demonstrate this overlooked fact on some synthetic and real datasets. The data and software related to this paper are available at https://mine. kaust.edu.sa/Pages/zero-shot-learning.aspx. © Springer International Publishing AG 2016.

Citation
Alabdulmohsin I, Cisse M, Zhang X (2016) Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy? Lecture Notes in Computer Science: 749–760. Available: http://dx.doi.org/10.1007/978-3-319-46128-1_47.

Acknowledgements
Research reported in this publication was supported by King Abdullah University of Science and Technology (KAUST) and the Saudi Arabian Oil Company (Saudi Aramco).

Publisher
Springer Nature

Journal
Machine Learning and Knowledge Discovery in Databases

Conference/Event Name
15th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2016

DOI
10.1007/978-3-319-46128-1_47

Additional Links
http://link.springer.com/chapter/10.1007%2F978-3-319-46128-1_47

Permanent link to this record