Hyperbolic Visual Embedding Learning for Zero-Shot Recognition
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9270-9278
Abstract
This paper proposes a Hyperbolic Visual Embedding Learning Network for zero-shot recognition. The network learns image embeddings in hyperbolic space, which is capable of preserving the hierarchical structure of semantic classes in low dimensions. Comparing with existing zero-shot learning approaches, the network is more robust because the embedding feature in hyperbolic space better represents class hierarchy and thereby avoid misleading resulted from unrelated siblings. Our network outperforms exiting baselines under hierarchical evaluation with an extremely challenging setting, \textit{i.e.,} learning only from 1,000 categories to recognize 20,841 unseen categories. While under flat evaluation, it has competitive performance as state-of-the-art methods but with five times lower embedding dimensions. Our code is publicly available \footnote{\url{https://github.com/ShaoTengLiu/Hyperbolic_ZSL}}.Keywords
This publication has 24 references indexed in Scilit:
- Synthesized Classifiers for Zero-Shot Learning2016
- Deep Residual Learning for Image Recognition2016
- Semi-supervised Vocabulary-Informed Learning2016
- Zero-Shot Learning via Semantic Similarity Embedding2015
- Linguistic Regularities in Sparse and Explicit Word Representations2014
- Glove: Global Vectors for Word Representation2014
- Attribute-Based Classification for Zero-Shot Visual Object CategorizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learning to share visual appearance for multiclass object detection2011
- Recognizing human actions by attributes2011
- WordNetCommunications of the ACM, 1995