Hyperbolic visual embedding learning for zero-shot recognition
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 zeroshot learning approaches...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6463 https://ink.library.smu.edu.sg/context/sis_research/article/7466/viewcontent/Liu_Hyperbolic_Visual_Embedding_Learning_for_Zero_Shot_Recognition_CVPR_2020_paper.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-7466 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-74662022-01-10T06:07:21Z Hyperbolic visual embedding learning for zero-shot recognition LIU, Shaoteng CHEN, Jingjing PAN, Liangming NGO, Chong-wah CHUA, Tat-Seng JIANG, Yu-Gang 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 zeroshot 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. 2020-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6463 info:doi/10.1109/CVPR42600.2020.00929 https://ink.library.smu.edu.sg/context/sis_research/article/7466/viewcontent/Liu_Hyperbolic_Visual_Embedding_Learning_for_Zero_Shot_Recognition_CVPR_2020_paper.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Databases and Information Systems Graphics and Human Computer Interfaces LIU, Shaoteng CHEN, Jingjing PAN, Liangming NGO, Chong-wah CHUA, Tat-Seng JIANG, Yu-Gang Hyperbolic visual embedding learning for zero-shot recognition |
description |
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 zeroshot 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. |
format |
text |
author |
LIU, Shaoteng CHEN, Jingjing PAN, Liangming NGO, Chong-wah CHUA, Tat-Seng JIANG, Yu-Gang |
author_facet |
LIU, Shaoteng CHEN, Jingjing PAN, Liangming NGO, Chong-wah CHUA, Tat-Seng JIANG, Yu-Gang |
author_sort |
LIU, Shaoteng |
title |
Hyperbolic visual embedding learning for zero-shot recognition |
title_short |
Hyperbolic visual embedding learning for zero-shot recognition |
title_full |
Hyperbolic visual embedding learning for zero-shot recognition |
title_fullStr |
Hyperbolic visual embedding learning for zero-shot recognition |
title_full_unstemmed |
Hyperbolic visual embedding learning for zero-shot recognition |
title_sort |
hyperbolic visual embedding learning for zero-shot recognition |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/6463 https://ink.library.smu.edu.sg/context/sis_research/article/7466/viewcontent/Liu_Hyperbolic_Visual_Embedding_Learning_for_Zero_Shot_Recognition_CVPR_2020_paper.pdf |
_version_ |
1770575967367987200 |