Zero-Shot Learning Posed as a Missing Data Problem
Authors:
- Bo ZhaoBZBo Zhao
- Botong WuBWBotong Wu
- Tianfu WuTWTianfu Wu
- Yizhou WangYWYizhou Wang
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2616-2622
Abstract
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature space to the label embedding space. Whereas, the proposed method explores a simple yet effective transductive framework in the reverse way - our method estimates data distribution of unseen classes in the image feature space by transferring knowledge from the label embedding space. Following the transductive setting, we leverage unlabeled data to refine the initial estimation. In experiments, our method achieves the highest classification accuracies on two popular datasets, namely, 96.00% on AwA and 60.24% on CUB.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Zero-Shot Recognition via Structured Prediction2016
- Zero-Shot Learning via Semantic Similarity Embedding2015
- Semi-Supervised Zero-Shot Classification with Label Representation Learning2015
- Unsupervised Domain Adaptation for Zero-Shot Learning2015
- Evaluation of output embeddings for fine-grained image classification2015
- Going deeper with convolutions2015
- Transductive Multi-View Zero-Shot LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- Sparse coding with an overcomplete basis set: A strategy employed by V1?Vision Research, 1997