Hyperbolic Visual Embedding Learning for Zero-Shot Recognition

Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, Yu-Gang Jiang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 9273-9281

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, 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 (https://github.com/ShaoTengLiu/Hyperbolic_ZSL).

Related Material


[pdf]
[bibtex]
@InProceedings{Liu_2020_CVPR,
author = {Liu, Shaoteng and Chen, Jingjing and Pan, Liangming and Ngo, Chong-Wah and Chua, Tat-Seng and Jiang, Yu-Gang},
title = {Hyperbolic Visual Embedding Learning for Zero-Shot Recognition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}