Semi-Supervised Zero-Shot Classification with Label Representation Learning
Full Text: 07410836.pdf
Given the challenge of gathering labeled training data, zero-shot classification, which transfers information from observed classes to recognize unseen classes, has become increasingly popular in the computer vision community. Most existing zero-shot learning methods require a user to first provide a set of semantic visual attributes for each class as side information before applying a two-step prediction procedure that introduces an intermediate attribute prediction problem. In this paper, we propose a novel zero-shot classification approach that automatically learns label embeddings from the input data in a semi-supervised large-margin learning framework. The proposed framework jointly considers multi-class classification over all classes (observed and unseen) and tackles the target prediction problem directly without introducing intermediate prediction problems. It also has the capacity to incorporate semantic label information from different sources when available. To evaluate the proposed approach, we conduct experiments on standard zero-shot data sets. The empirical results show the proposed approach outperforms existing state-of-the-art zero-shot learning methods.
Citation
X. Li, Y. Guo, D. Schuurmans. "Semi-Supervised Zero-Shot Classification with Label Representation Learning". IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, December 2015.| Keywords: | |
| Category: | In Conference |
| Web Links: | IEEE |
BibTeX
@incollection{Li+al:IEEEICCV15,
author = {Xin Li and Yuhong Guo and Dale Schuurmans},
title = {Semi-Supervised Zero-Shot Classification with Label Representation
Learning},
booktitle = {IEEE International Conference on Computer Vision (ICCV)},
year = 2015,
}Last Updated: September 10, 2020Submitted by Sabina P
