Saved in:
Bibliographic Details
Main Authors: Koutoupis, Stefanos, Zervou, Michaela Areti, Kontras, Konstantinos, De Vos, Maarten, Tsakalides, Panagiotis, Tsagkatakis, Grigorios
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.21331
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911564050726912
author Koutoupis, Stefanos
Zervou, Michaela Areti
Kontras, Konstantinos
De Vos, Maarten
Tsakalides, Panagiotis
Tsagkatakis, Grigorios
author_facet Koutoupis, Stefanos
Zervou, Michaela Areti
Kontras, Konstantinos
De Vos, Maarten
Tsakalides, Panagiotis
Tsagkatakis, Grigorios
contents Learning joint representations across multiple modalities remains a central challenge in multimodal machine learning. Prevailing approaches predominantly operate in pairwise settings, aligning two modalities at a time. While some recent methods aim to capture higher-order interactions among multiple modalities, they often overlook or insufficiently preserve pairwise relationships, limiting their effectiveness on single-modality tasks. In this work, we introduce Contrastive Fusion (ConFu), a framework that jointly embeds both individual modalities and their fused combinations into a unified representation space, where modalities and their fused counterparts are aligned. ConFu extends traditional pairwise contrastive objectives with an additional fused-modality contrastive term, encouraging the joint embedding of modality pairs with a third modality. This formulation enables ConFu to capture higher-order dependencies, such as XOR-like relationships, that cannot be recovered through pairwise alignment alone, while still maintaining strong pairwise correspondence. We evaluate ConFu on synthetic and real-world multimodal benchmarks, assessing its ability to exploit cross-modal complementarity, capture higher-order dependencies, and scale with increasing multimodal complexity. Across these settings, ConFu demonstrates competitive performance on retrieval and classification tasks, while supporting unified one-to-one and two-to-one retrieval within a single contrastive framework. We release our code and dataset at https://github.com/estafons/confu.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21331
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment
Koutoupis, Stefanos
Zervou, Michaela Areti
Kontras, Konstantinos
De Vos, Maarten
Tsakalides, Panagiotis
Tsagkatakis, Grigorios
Computer Vision and Pattern Recognition
Artificial Intelligence
Learning joint representations across multiple modalities remains a central challenge in multimodal machine learning. Prevailing approaches predominantly operate in pairwise settings, aligning two modalities at a time. While some recent methods aim to capture higher-order interactions among multiple modalities, they often overlook or insufficiently preserve pairwise relationships, limiting their effectiveness on single-modality tasks. In this work, we introduce Contrastive Fusion (ConFu), a framework that jointly embeds both individual modalities and their fused combinations into a unified representation space, where modalities and their fused counterparts are aligned. ConFu extends traditional pairwise contrastive objectives with an additional fused-modality contrastive term, encouraging the joint embedding of modality pairs with a third modality. This formulation enables ConFu to capture higher-order dependencies, such as XOR-like relationships, that cannot be recovered through pairwise alignment alone, while still maintaining strong pairwise correspondence. We evaluate ConFu on synthetic and real-world multimodal benchmarks, assessing its ability to exploit cross-modal complementarity, capture higher-order dependencies, and scale with increasing multimodal complexity. Across these settings, ConFu demonstrates competitive performance on retrieval and classification tasks, while supporting unified one-to-one and two-to-one retrieval within a single contrastive framework. We release our code and dataset at https://github.com/estafons/confu.
title The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.21331