Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

Jeong Cheol Lee; Athul Shibu; Dong Gyu Lee

doi:10.1109/ICCE56470.2023.10043553

Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

Jeong Cheol Lee
, Athul Shibu
, Dong Gyu Lee

School of Electronics Engineering

Kyungpook National University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.

Original language	English
Title of host publication	2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665491303
DOIs	https://doi.org/10.1109/ICCE56470.2023.10043553
State	Published - 2023
Event	2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States Duration: 6 Jan 2023 → 8 Jan 2023

Publication series

Name	Digest of Technical Papers - IEEE International Conference on Consumer Electronics
Volume	2023-January
ISSN (Print)	0747-668X

Conference

Conference	2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Country/Territory	United States
City	Las Vegas
Period	6/01/23 → 8/01/23

Keywords

Adaptive margin
contrastive network
deep learning
generalized zero-shot learning
zero-shot learning

Access to Document

10.1109/ICCE56470.2023.10043553

Cite this

Lee, J. C., Shibu, A., & Lee, D. G. (2023). Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning. In 2023 IEEE International Conference on Consumer Electronics, ICCE 2023 (Digest of Technical Papers - IEEE International Conference on Consumer Electronics; Vol. 2023-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE56470.2023.10043553

@inproceedings{68e7b93fc49843488b106548f8eb5006,

title = "Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning",

abstract = "Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.",

keywords = "Adaptive margin, contrastive network, deep learning, generalized zero-shot learning, zero-shot learning",

author = "Lee, \{Jeong Cheol\} and Athul Shibu and Lee, \{Dong Gyu\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Consumer Electronics, ICCE 2023 ; Conference date: 06-01-2023 Through 08-01-2023",

year = "2023",

doi = "10.1109/ICCE56470.2023.10043553",

language = "English",

series = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE International Conference on Consumer Electronics, ICCE 2023",

address = "United States",

}

Lee, JC, Shibu, A & Lee, DG 2023, Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning. in 2023 IEEE International Conference on Consumer Electronics, ICCE 2023. Digest of Technical Papers - IEEE International Conference on Consumer Electronics, vol. 2023-January, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Conference on Consumer Electronics, ICCE 2023, Las Vegas, United States, 6/01/23. https://doi.org/10.1109/ICCE56470.2023.10043553

Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning. / Lee, Jeong Cheol; Shibu, Athul; Lee, Dong Gyu.
2023 IEEE International Conference on Consumer Electronics, ICCE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Digest of Technical Papers - IEEE International Conference on Consumer Electronics; Vol. 2023-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

AU - Lee, Jeong Cheol

AU - Shibu, Athul

AU - Lee, Dong Gyu

PY - 2023

Y1 - 2023

N2 - Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.

AB - Generalized zero-shot learning is a challenging problem that aims to recognize images from seen and unseen classes. Recent methods are costly and time-consuming or have a bias problem. To tackle this problem, we proposed an adaptive margin-based contrastive network that aims to distinguish similar classes in generalized zero-shot learning. The proposed method employs the architecture of transferable contrastive network to classify unseen classes and adaptive margin to transfer discriminative knowledge. Experiments on the AwA2 dataset demonstrate competitive results against state-of-the-art benchmarks.

KW - Adaptive margin

KW - contrastive network

KW - deep learning

KW - generalized zero-shot learning

KW - zero-shot learning

UR - https://www.scopus.com/pages/publications/85149129997

U2 - 10.1109/ICCE56470.2023.10043553

DO - 10.1109/ICCE56470.2023.10043553

M3 - Conference contribution

AN - SCOPUS:85149129997

T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

BT - 2023 IEEE International Conference on Consumer Electronics, ICCE 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Consumer Electronics, ICCE 2023

Y2 - 6 January 2023 through 8 January 2023

ER -

Adaptive Margin-based Contrastive Network for Generalized Zero-Shot Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this