Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

About

In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or video-audio pairs). Underpinning these approaches is the assumption of multi-view redundancy - that shared information between modalities is necessary and sufficient for downstream tasks. However, in many real-world settings, task-relevant information is also contained in modality-unique regions: information that is only present in one modality but still relevant to the task. How can we learn self-supervised multimodal representations to capture both shared and unique information relevant to downstream tasks? This paper proposes FactorCL, a new multimodal representation learning method to go beyond multi-view redundancy. FactorCL is built from three new contributions: (1) factorizing task-relevant information into shared and unique representations, (2) capturing task-relevant information via maximizing MI lower bounds and removing task-irrelevant information via minimizing MI upper bounds, and (3) multimodal data augmentations to approximate task relevance without labels. On large-scale real-world datasets, FactorCL captures both shared and unique information and achieves state-of-the-art results on six benchmarks

Paul Pu Liang, Zihao Deng, Martin Ma, James Zou, Louis-Philippe Morency, Ruslan Salakhutdinov• 2023

Related benchmarks

TaskDatasetResultRank
Image ClassificationMNIST
Accuracy99.21
395
Multimodal Sentiment AnalysisCMU-MOSI--
59
Sentiment AnalysisCMU-MOSEI (test)--
40
Multimodal Sentiment AnalysisMOSEI--
22
Humor DetectionUR-FUNNY--
20
Image-Text ClassificationIRFL
Accuracy98.8
16
Sarcasm DetectionMUSTARD
Accuracy69.9
13
ClassificationMIMIC
Accuracy76.8
8
Multimodal ClassificationMIMIC
Accuracy0.7679
8
Multimodal ClassificationMOSI
Accuracy70.69
8
Showing 10 of 13 rows

Other info

Code

Follow for update