Transductive Unbiased Embedding for Zero-Shot Learning

Jie Song, Chengchao Shen, Yezhou Yang, Yang Liu, Mingli Song

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5% following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2% following conventional ZSL settings.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PublisherIEEE Computer Society
Pages1024-1033
Number of pages10
ISBN (Electronic)9781538664209
DOIs
StatePublished - Dec 14 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States
Duration: Jun 18 2018Jun 22 2018

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
CountryUnited States
CitySalt Lake City
Period6/18/186/22/18

Fingerprint

Supervised learning
Semantics
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Song, J., Shen, C., Yang, Y., Liu, Y., & Song, M. (2018). Transductive Unbiased Embedding for Zero-Shot Learning. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 1024-1033). [8578211] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00113

Transductive Unbiased Embedding for Zero-Shot Learning. / Song, Jie; Shen, Chengchao; Yang, Yezhou; Liu, Yang; Song, Mingli.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 1024-1033 8578211 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Song, J, Shen, C, Yang, Y, Liu, Y & Song, M 2018, Transductive Unbiased Embedding for Zero-Shot Learning. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018., 8578211, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 1024-1033, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, United States, 6/18/18. https://doi.org/10.1109/CVPR.2018.00113
Song J, Shen C, Yang Y, Liu Y, Song M. Transductive Unbiased Embedding for Zero-Shot Learning. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society. 2018. p. 1024-1033. 8578211. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2018.00113
Song, Jie ; Shen, Chengchao ; Yang, Yezhou ; Liu, Yang ; Song, Mingli. / Transductive Unbiased Embedding for Zero-Shot Learning. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. pp. 1024-1033 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{05cb7d6c1af64689b6bd22f202a04fa0,
title = "Transductive Unbiased Embedding for Zero-Shot Learning",
abstract = "Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5{\%} following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2{\%} following conventional ZSL settings.",
author = "Jie Song and Chengchao Shen and Yezhou Yang and Yang Liu and Mingli Song",
year = "2018",
month = "12",
day = "14",
doi = "10.1109/CVPR.2018.00113",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "1024--1033",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018",

}

TY - GEN

T1 - Transductive Unbiased Embedding for Zero-Shot Learning

AU - Song, Jie

AU - Shen, Chengchao

AU - Yang, Yezhou

AU - Liu, Yang

AU - Song, Mingli

PY - 2018/12/14

Y1 - 2018/12/14

N2 - Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5% following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2% following conventional ZSL settings.

AB - Most existing Zero-Shot Learning (ZSL) methods have the strong bias problem, in which instances of unseen (target) classes tend to be categorized as one of the seen (source) classes. So they yield poor performance after being deployed in the generalized ZSL settings. In this paper, we propose a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem. Our method follows the way of transductive learning, which assumes that both the labeled source images and unlabeled target images are available for training. In the semantic embedding space, the labeled source images are mapped to several fixed points specified by the source categories, and the unlabeled target images are forced to be mapped to other points specified by the target categories. Experiments conducted on AwA2, CUB and SUN datasets demonstrate that our method outperforms existing state-of-the-art approaches by a huge margin of 9.3 ~ 24.5% following generalized ZSL settings, and by a large margin of 0.2 ~ 16.2% following conventional ZSL settings.

UR - http://www.scopus.com/inward/record.url?scp=85055116030&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055116030&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2018.00113

DO - 10.1109/CVPR.2018.00113

M3 - Conference contribution

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1024

EP - 1033

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

PB - IEEE Computer Society

ER -