Revealing Multimodal Contrastive Representation Learning through Latent Partial Causal Models

No abstract is available for this paper.

• Publication year

  2024

• Venue

  arXiv.org

• Publication date

  Unknown publication date

• Fields of study

  Computer Science

• Identifiers
  DOI 10.48550/arXiv.2402.06223
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multi-View Causal Representation Learning with Partial Observability

  2023influential reference
• Identifiability Results for Multimodal Contrastive Learning

  2023influential reference
• Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data

  2023cited by this paper
• Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

  2022cited by this paper
• Conditional Prompt Learning for Vision-Language Models

  2022cited by this paper
• Pre-trained Adversarial Perturbations

  2022cited by this paper
• Image Segmentation Using Text and Image Prompts

  2021cited by this paper
• Toward Causal Representation Learning

  2021cited by this paper
• Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

  2021influential reference
• What Makes Multimodal Learning Better than Single (Provably)

  2021cited by this paper
• Contrastive Learning Inverts the Data Generating Process

  2021influential reference
• Learning Transferable Visual Models From Natural Language Supervision

  2021influential reference
• Learning to Prompt for Vision-Language Models

  2021cited by this paper
• A Simple Framework for Contrastive Learning of Visual Representations

  2020cited by this paper
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere

  2020influential reference
• The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

  2020cited by this paper
• Contrastive Learning of Medical Visual Representations from Paired Images and Text

  2020cited by this paper
• Natural Adversarial Examples

  2019cited by this paper
• Learning Robust Global Representations by Penalizing Local Predictive Power

  2019cited by this paper
• Contrastive Multiview Coding

  2019cited by this paper
• Variational Autoencoders and Nonlinear ICA: A Unifying Framework

  2019cited by this paper
• Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models

  2019cited by this paper
• Do ImageNet Classifiers Generalize to ImageNet?

  2019cited by this paper
• A Theoretical Analysis of Contrastive Unsupervised Representation Learning

  2019cited by this paper
• The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA

  2019influential reference
• Representation Learning with Contrastive Predictive Coding

  2018cited by this paper
• Disentangling by Factorising

  2018cited by this paper
• Unsupervised Feature Learning via Non-parametric Instance Discrimination

  2018cited by this paper
• Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning

  2018cited by this paper
• Isolating Sources of Disentanglement in Variational Autoencoders

  2018cited by this paper
• Fine-Grained Image Classification via Combining Vision and Language

  2017cited by this paper
• Nonlinear ICA of Temporally Dependent Stationary Sources

  2017cited by this paper
• Uniform Convergence Rates for Kernel Density Estimation

  2017cited by this paper
• Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA

  2016cited by this paper
• Invariant Models for Causal Transfer Learning

  2015cited by this paper
• Deep Learning Face Attributes in the Wild

  2014cited by this paper
• A Sentence Is Worth a Thousand Pixels

  2013cited by this paper
• Video Event Understanding Using Natural Language Descriptions

  2013cited by this paper
• A picture is worth a thousand words: A content analysis of Facebook profile photographs

  2011cited by this paper
• Noise-contrastive estimation: A new estimation principle for unnormalized statistical models

  2010cited by this paper
• ImageNet: A large-scale hierarchical image database

  2009cited by this paper
• Learning Models for Object Recognition from Natural Language Descriptions

  2009cited by this paper
• Learning Visual Representations using Images with Captions

  2007cited by this paper
• Independent Component Analysis

  2005influential reference
• Fast and robust fixed-point algorithms for independent component analysis

  1999cited by this paper
• Image-to-word transformation based on dividing and vector quantizing images with words

  1999cited by this paper
• Nonlinear independent component analysis: Existence and uniqueness results

  1999cited by this paper
• One picture is worth a thousand words? Not necessarily.

  1976cited by this paper
• Why is a picture worth a thousand words?

  1963cited by this paper

• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?

  2025cites this paper
• On the Value of Cross-Modal Misalignment in Multimodal Representation Learning

  2025influential citation
• Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables

  2025cites this paper
• Negate or Embrace: On How Misalignment Shapes Multimodal Representation Learning

  2025influential citation
• Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning

  2025cites this paper
• Calibrated Self-Rewarding Vision Language Models

  2024cites this paper