Group-based siamese self-supervised learning

In this paper, we introduced a novel group self-supervised learning approach designed to improve visual representation learning. This new method aimed to rectify the limitations observed in conventional self-supervised learning. Traditional methods tended to focus on embedding distortion-invariant i...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongnian Li, Jiayu Wang, Qingcong Geng, Xinzheng Xu
Format: Article
Language:English
Published: AIMS Press 2024-08-01
Series:Electronic Research Archive
Subjects:
Online Access:https://www.aimspress.com/article/doi/10.3934/era.2024226
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590812661153792
author Zhongnian Li
Jiayu Wang
Qingcong Geng
Xinzheng Xu
author_facet Zhongnian Li
Jiayu Wang
Qingcong Geng
Xinzheng Xu
author_sort Zhongnian Li
collection DOAJ
description In this paper, we introduced a novel group self-supervised learning approach designed to improve visual representation learning. This new method aimed to rectify the limitations observed in conventional self-supervised learning. Traditional methods tended to focus on embedding distortion-invariant in single-view features. However, our belief was that a better representation can be achieved by creating a group of features derived from multiple views. To expand the siamese self-supervised architecture, we increased the number of image instances in each crop, enabling us to obtain an average feature from a group of views to use as a distortion, invariant embedding. The training efficiency has greatly increased with rapid convergence. When combined with a robust linear protocol, this group self-supervised learning model achieved competitive results in CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet-100 classification tasks. Most importantly, our model demonstrated significant convergence gains within just 30 epochs as opposed to the typical 1000 epochs required by most other self-supervised techniques.
format Article
id doaj-art-544b1122be244001a1ddaa61186fa09e
institution Kabale University
issn 2688-1594
language English
publishDate 2024-08-01
publisher AIMS Press
record_format Article
series Electronic Research Archive
spelling doaj-art-544b1122be244001a1ddaa61186fa09e2025-01-23T07:51:27ZengAIMS PressElectronic Research Archive2688-15942024-08-013284913492510.3934/era.2024226Group-based siamese self-supervised learningZhongnian Li0Jiayu Wang1Qingcong Geng2Xinzheng Xu3School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, ChinaIn this paper, we introduced a novel group self-supervised learning approach designed to improve visual representation learning. This new method aimed to rectify the limitations observed in conventional self-supervised learning. Traditional methods tended to focus on embedding distortion-invariant in single-view features. However, our belief was that a better representation can be achieved by creating a group of features derived from multiple views. To expand the siamese self-supervised architecture, we increased the number of image instances in each crop, enabling us to obtain an average feature from a group of views to use as a distortion, invariant embedding. The training efficiency has greatly increased with rapid convergence. When combined with a robust linear protocol, this group self-supervised learning model achieved competitive results in CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet-100 classification tasks. Most importantly, our model demonstrated significant convergence gains within just 30 epochs as opposed to the typical 1000 epochs required by most other self-supervised techniques.https://www.aimspress.com/article/doi/10.3934/era.2024226self-supervised learningaverage featuremultiple viewsclassification taskssiamese network
spellingShingle Zhongnian Li
Jiayu Wang
Qingcong Geng
Xinzheng Xu
Group-based siamese self-supervised learning
Electronic Research Archive
self-supervised learning
average feature
multiple views
classification tasks
siamese network
title Group-based siamese self-supervised learning
title_full Group-based siamese self-supervised learning
title_fullStr Group-based siamese self-supervised learning
title_full_unstemmed Group-based siamese self-supervised learning
title_short Group-based siamese self-supervised learning
title_sort group based siamese self supervised learning
topic self-supervised learning
average feature
multiple views
classification tasks
siamese network
url https://www.aimspress.com/article/doi/10.3934/era.2024226
work_keys_str_mv AT zhongnianli groupbasedsiameseselfsupervisedlearning
AT jiayuwang groupbasedsiameseselfsupervisedlearning
AT qingconggeng groupbasedsiameseselfsupervisedlearning
AT xinzhengxu groupbasedsiameseselfsupervisedlearning