Max-Margin Zero-Shot Learning for Multi-class Classification

Xin Li, Yuhong Guo
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, PMLR 38:626-634, 2015.

Abstract

Due to the dramatic expanse of data categories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semi-supervised classification problem over observed classes and the unsupervised clustering problem over unseen classes together to tackle zero-shot multi-class classification. By further integrating label embedding into this framework, we produce a dual formulation that permits convenient incorporation of auxiliary label semantic knowledge to improve zero-shot learning. We conduct extensive experiments on three standard image data sets to evaluate the proposed approach by comparing to two state-of-the-art methods. Our results demonstrate the efficacy of the proposed framework.

Cite this Paper


BibTeX
@InProceedings{pmlr-v38-li15d, title = {{Max-Margin Zero-Shot Learning for Multi-class Classification}}, author = {Li, Xin and Guo, Yuhong}, booktitle = {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics}, pages = {626--634}, year = {2015}, editor = {Lebanon, Guy and Vishwanathan, S. V. N.}, volume = {38}, series = {Proceedings of Machine Learning Research}, address = {San Diego, California, USA}, month = {09--12 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v38/li15d.pdf}, url = {https://proceedings.mlr.press/v38/li15d.html}, abstract = {Due to the dramatic expanse of data categories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semi-supervised classification problem over observed classes and the unsupervised clustering problem over unseen classes together to tackle zero-shot multi-class classification. By further integrating label embedding into this framework, we produce a dual formulation that permits convenient incorporation of auxiliary label semantic knowledge to improve zero-shot learning. We conduct extensive experiments on three standard image data sets to evaluate the proposed approach by comparing to two state-of-the-art methods. Our results demonstrate the efficacy of the proposed framework.} }
Endnote
%0 Conference Paper %T Max-Margin Zero-Shot Learning for Multi-class Classification %A Xin Li %A Yuhong Guo %B Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2015 %E Guy Lebanon %E S. V. N. Vishwanathan %F pmlr-v38-li15d %I PMLR %P 626--634 %U https://proceedings.mlr.press/v38/li15d.html %V 38 %X Due to the dramatic expanse of data categories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semi-supervised classification problem over observed classes and the unsupervised clustering problem over unseen classes together to tackle zero-shot multi-class classification. By further integrating label embedding into this framework, we produce a dual formulation that permits convenient incorporation of auxiliary label semantic knowledge to improve zero-shot learning. We conduct extensive experiments on three standard image data sets to evaluate the proposed approach by comparing to two state-of-the-art methods. Our results demonstrate the efficacy of the proposed framework.
RIS
TY - CPAPER TI - Max-Margin Zero-Shot Learning for Multi-class Classification AU - Xin Li AU - Yuhong Guo BT - Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics DA - 2015/02/21 ED - Guy Lebanon ED - S. V. N. Vishwanathan ID - pmlr-v38-li15d PB - PMLR DP - Proceedings of Machine Learning Research VL - 38 SP - 626 EP - 634 L1 - http://proceedings.mlr.press/v38/li15d.pdf UR - https://proceedings.mlr.press/v38/li15d.html AB - Due to the dramatic expanse of data categories and the lack of labeled instances, zero-shot learning, which transfers knowledge from observed classes to recognize unseen classes, has started drawing a lot of attention from the research community. In this paper, we propose a semi-supervised max-margin learning framework that integrates the semi-supervised classification problem over observed classes and the unsupervised clustering problem over unseen classes together to tackle zero-shot multi-class classification. By further integrating label embedding into this framework, we produce a dual formulation that permits convenient incorporation of auxiliary label semantic knowledge to improve zero-shot learning. We conduct extensive experiments on three standard image data sets to evaluate the proposed approach by comparing to two state-of-the-art methods. Our results demonstrate the efficacy of the proposed framework. ER -
APA
Li, X. & Guo, Y.. (2015). Max-Margin Zero-Shot Learning for Multi-class Classification. Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 38:626-634 Available from https://proceedings.mlr.press/v38/li15d.html.

Related Material