DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning

doi:10.1109/ACCESS.2023.3236087

DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning

2023-01-01

6

OA

AI

DOI：10.1109/ACCESS.2023.3236087

Original

Original request for help

Save

Abstract

En 中文

Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance with high improvement potential, prompting researchers to enhance these frameworks further. Assimilating CL into non-CL frameworks has been thought to be beneficial, but empirical evidence indicates no visible improvements. In view of that, this paper proposes a strategy of performing CL along the dimensional direction instead of along the batch direction as done in conventional contrastive learning, named Dimensional Contrastive Learning (DimCL). DimCL aims to enhance the feature diversity, and it can serve as a regularizer to prior SSL frameworks. DimCL has been found to be effective, and the hardness-aware property is identified as a critical reason for its success. Extensive experimental results reveal that assimilating DimCL into SSL frameworks leads to performance improvement by a non-trivial margin on various datasets and backbone architectures.

Keywords:

Transfer learning

Task analysis

Self-supervised learning

Learning systems

Loss measurement

Computer vision

Self-supervise learning

computer vision

contrastive learning

deep learning

transfer learning

DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning

Abstract

Journal

Organization