Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning

Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1232-1241

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 attribute-class 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Demirel_2017_ICCV,
author = {Demirel, Berkan and Gokberk Cinbis, Ramazan and Ikizler-Cinbis, Nazli},
title = {Attributes2Classname: A Discriminative Model for Attribute-Based Unsupervised Zero-Shot Learning},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}