Transductive Unbiased Embedding for Zero-Shot Learning
Authors:
- Jie SongJSJie Song
- Chengchao ShenCSChengchao Shen
- Yezhou YangYYYezhou Yang
- Yang LiuYLYang Liu
- Mingli SongMSMingli Song
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1024-1033
Abstract
Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5% following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2% following conventional ZSL settings.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Ridge Regression, Hubness, and Zero-Shot Learning2015
- Evaluation of output embeddings for fine-grained image classification2015
- Going deeper with convolutions2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Transductive Multi-View Zero-Shot LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Glove: Global Vectors for Word Representation2014
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- SUN attribute database: Discovering, annotating, and recognizing scene attributes2012
- Learning to share visual appearance for multiclass object detection2011
- WordNetCommunications of the ACM, 1995