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!
Description
Summary: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.
ISSN:2688-1594