Show simple item record

dc.contributor.authorAlabdulmohsin, Ibrahim
dc.contributor.authorCisse, Moustapha
dc.contributor.authorZhang, Xiangliang
dc.date.accessioned2017-01-02T08:10:21Z
dc.date.available2017-01-02T08:10:21Z
dc.date.issued2016-09-04
dc.identifier.citationAlabdulmohsin 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.
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.doi10.1007/978-3-319-46128-1_47
dc.identifier.urihttp://hdl.handle.net/10754/622148
dc.description.abstractOne 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.
dc.description.sponsorshipResearch reported in this publication was supported by King Abdullah University of Science and Technology (KAUST) and the Saudi Arabian Oil Company (Saudi Aramco).
dc.publisherSpringer Nature
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-46128-1_47
dc.subjectAttribute-based classification
dc.subjectMultilabel classification
dc.subjectZero-shot learning
dc.titleIs Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalMachine Learning and Knowledge Discovery in Databases
dc.conference.date2016-09-19 to 2016-09-23
dc.conference.name15th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2016
dc.conference.locationRiva del Garda, ITA
dc.contributor.institutionFacebook Artificial Intelligence Research (FAIR), Menlo Park, United States
kaust.personAlabdulmohsin, Ibrahim
kaust.personZhang, Xiangliang
dc.date.published-online2016-09-04
dc.date.published-print2016


This item appears in the following Collection(s)

Show simple item record