paper-with-me

홈 › Papers

Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables

2025-05-18 · Yu Gui, Cong Ma, Zongming Ma

Multi-modal contrastive learning as a self-supervised representation learning technique has achieved great success in foundation model training, such as CLIP~\citep{radford2021learning}. In this paper, we study the theoretical properties of the learned representations from multi-modal contrastive learning beyond linear representations and specific data distributions. Our analysis reveals that, enabled by temperature optimization, multi-modal contrastive learning not only maximizes mutual information between modalities but also adapts to intrinsic dimensions of data, which can be much lower than user-specified dimensions for representation vectors. Experiments on both synthetic and real-world datasets demonstrate the ability of contrastive learning to learn low-dimensional and informative representations, bridging theoretical insights and practical performance.

📄 PDF Abstract BibTeX arXiv:2505.12473

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning

2026-02-09 · Jinjin Guo, Yexin Li, Zhichao Huang, Jun Fang 외 arxiv

Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the uniform treatment of feature dimensions …

Representation LearningContrastive Learning

Breaking the Geometric Bottleneck: Contrastive Expansion in Asymmetric Cross-Modal Distillation

2026-03-05 · Kabir Thayani arxiv

Knowledge distillation between asymmetric architectures often induces severe geometric constraints on the learned representation space. In this work, we investigate the Dimensional Collapse phenomenon when distilling glo…

Knowledge Distillation

CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization

2024-09-09 · Nan Chen, Mengqi Huang, Zhuowei Chen, Yang Zheng 외

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a s…

Contrastive Learning

AMMASurv: Asymmetrical Multi-Modal Attention for Accurate Survival Analysis with Whole Slide Images and Gene Expression Data

2021-08-28 · Ruoqi Wang, Ziwang Huang, Haitao Wang, Hejun Wu

The use of multi-modal data such as the combination of whole slide images (WSIs) and gene expression data for survival analysis can lead to more accurate survival predictions. Previous multi-modal survival models are not…

Survival AnalysisSurvival Predictionwhole slide images

Audio-Vision Contrastive Learning for Phonological Class Recognition

2025-07-23 · Daiqi Liu, Tomás Arias-Vergara, Jana Hutter, Andreas Maier 외 arxiv

Accurate classification of articulatory-phonological features plays a vital role in understanding human speech production and developing robust speech technologies, particularly in clinical contexts where targeted phonem…

Multimodal Deep LearningRepresentation LearningContrastive Learning