paper-with-me

Papers

DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning

2023-09-21 · Thanh Nguyen, Trung Pham, Chaoning Zhang, Tung Luu, Thang Vu, Chang D. Yoo

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.

📄 PDF Abstract BibTeX arXiv:2309.11782

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningDiversitySelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Supervised Stochastic Neighbor Embedding Using Contrastive Learning

2023-09-15 · Yi Zhang

Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization. Contrastive learning, especially self-supervised contrastive learning (SSCL), has sh…

Contrastive LearningData VisualizationDimensionality Reduction

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

2021-10-18 · ICLR 2022 4 · Li Jing, Pascal Vincent, Yann Lecun, Yuandong Tian

Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from differen…

Contrastive LearningLearning TheoryRepresentation LearningSelf-Supervised Learning

Unified Framework for Feature Extraction based on Contrastive Learning

2021-01-25 · Hongjie Zhang

Feature extraction is an efficient approach for alleviating the issue of dimensionality in high-dimensional data. As a popular self-supervised learning method, contrastive learning has recently garnered considerable atte…

Contrastive LearningGraph EmbeddingSelf-Supervised Learning

MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning

2022-09-16 · Jiangmeng Li, Wenwen Qiang, Yanan Zhang, Wenyi Mo 외

As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements …

Contrastive LearningMeta-LearningSelf-Supervised Learning

From Pretext to Purpose: Batch-Adaptive Self-Supervised Learning

2023-11-16 · Jiansong Zhang, Linlin Shen, Peizhong Liu

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…

Contrastive LearningDimensionality ReductionSelf-Supervised Learning