@article{Li2024, 
author = {Zhongnian Li and Jiayu Wang and Qingcong Geng and Xinzheng Xu},
title = {Group-based siamese self-supervised learning},
year = {2024},
journal = {Electronic Research Archive},
volume = {32},
number = {8},
pages = {4913-4925},
keywords = {self-supervised learning, average feature, multiple views, classification tasks, siamese network},
url = {https://www.sciopen.com/article/10.3934/era.2024226},
doi = {10.3934/era.2024226},
abstract = {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.}
}