Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Jiansong, Shen, Linlin, Liu, Peizhong
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.09974
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909150562222080
author Zhang, Jiansong
Shen, Linlin
Liu, Peizhong
author_facet Zhang, Jiansong
Shen, Linlin
Liu, Peizhong
contents In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level. However, crafting an effective self-supervised paradigm remains a pivotal challenge within this field. This paper delves into two crucial factors impacting self-supervised contrastive learning-bach size and pretext tasks, and from a data processing standpoint, proposes an adaptive technique of batch fusion. The proposed method, via dimensionality reduction and reconstruction of batch data, enables formerly isolated individual data to partake in intra-batch communication through the Embedding Layer. Moreover, it adaptively amplifies the self-supervised feature encoding capability as the training progresses. We conducted a linear classification test of this method based on the classic contrastive learning framework on ImageNet-1k. The empirical findings illustrate that our approach achieves state-of-the-art performance under equitable comparisons. Benefiting from its "plug-and-play" characteristics, we further explored other contrastive learning methods. On the ImageNet-100, compared to the original performance, the top1 has seen a maximum increase of 1.25%. We suggest that the proposed method may contribute to the advancement of data-driven self-supervised learning research, bringing a fresh perspective to this community.
format Preprint
id arxiv_https___arxiv_org_abs_2311_09974
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle From Pretext to Purpose: Batch-Adaptive Self-Supervised Learning
Zhang, Jiansong
Shen, Linlin
Liu, Peizhong
Computer Vision and Pattern Recognition
In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level. However, crafting an effective self-supervised paradigm remains a pivotal challenge within this field. This paper delves into two crucial factors impacting self-supervised contrastive learning-bach size and pretext tasks, and from a data processing standpoint, proposes an adaptive technique of batch fusion. The proposed method, via dimensionality reduction and reconstruction of batch data, enables formerly isolated individual data to partake in intra-batch communication through the Embedding Layer. Moreover, it adaptively amplifies the self-supervised feature encoding capability as the training progresses. We conducted a linear classification test of this method based on the classic contrastive learning framework on ImageNet-1k. The empirical findings illustrate that our approach achieves state-of-the-art performance under equitable comparisons. Benefiting from its "plug-and-play" characteristics, we further explored other contrastive learning methods. On the ImageNet-100, compared to the original performance, the top1 has seen a maximum increase of 1.25%. We suggest that the proposed method may contribute to the advancement of data-driven self-supervised learning research, bringing a fresh perspective to this community.
title From Pretext to Purpose: Batch-Adaptive Self-Supervised Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.09974