Semantic Autoencoder for Zero-Shot Learning
Authors:
- Elyor KodirovEKElyor Kodirov
- Tao XiangTXTao Xiang
- Shaogang GongSGShaogang Gong
Top Cited Papers
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 4447-4456
Abstract
Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g. attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g. attribute prediction) or classification. When applied to test data, which in the context of ZSL contains different (unseen) classes without training data, a ZSL model typically suffers from the project domain shift problem. In this work, we present a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE). Taking the encoder-decoder paradigm, an encoder aims to project a visual feature vector into the semantic space as in the existing ZSL models. However, the decoder exerts an additional constraint, that is, the projection/code must be able to reconstruct the original visual feature. We show that with this additional reconstruction constraint, the learned projection function from the seen classes is able to generalise better to the new unseen classes. Importantly, the encoder and decoder are linear and symmetric which enable us to develop an extremely efficient learning algorithm. Extensive experiments on six benchmark datasets demonstrate that the proposed SAE outperforms significantly the existing ZSL models with the additional benefit of lower computational cost. Furthermore, when the SAE is applied to supervised clustering problem, it also beats the state-of-the-art.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Ridge Regression, Hubness, and Zero-Shot Learning2015
- 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
- The SUN Attribute Database: Beyond Categories for Deeper Scene UnderstandingInternational Journal of Computer Vision, 2014
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- A tutorial on spectral clusteringStatistics and Computing, 2007
- Neural networks and principal component analysis: Learning from examples without local minimaNeural Networks, 1989
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987
- Algorithm 432 [C2]: Solution of the matrix equation AX + XB = C [F4]Communications of the ACM, 1972