Attributes2Classname: a discriminative model for attribute-based unsupervised zero-shot learning
Date
2017-10Source Title
Proceedings of the IEEE International Conference on Computer Vision
Publisher
IEEE
Pages
1241 - 1250
Language
English
Type
Conference PaperItem Usage Stats
215
views
views
265
downloads
downloads
Abstract
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively learn a word representation such that the similarities between class and combination of attribute names fall in line with the visual similarity. Contrary to the traditional zero-shot learning approaches that are built upon attribute presence, our approach bypasses the laborious attributeclass relation annotations for unseen classes. In addition, our proposed approach renders text-only training possible, hence, the training can be augmented without the need to collect additional image data. The experimental results show that our method yields state-of-the-art results for unsupervised ZSL in three benchmark datasets. © 2017 IEEE.
Keywords
SemanticsVector spaces
Attribute-based
Benchmark datasets
Discriminative models
Image features
Learning approach
State of the art
Visual similarity
Word representations
Computer vision