Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning

Date

2017-01-01

Author

Demirel, Berkan
Cinbiş, Ramazan Gökberk
İKİZLER CİNBİŞ, NAZLI

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

7
views

5
downloads

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.

URI

https://hdl.handle.net/11511/56546

Collections

Department of Computer Engineering, Conference / Seminar