Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Madaan, Divyam, Makino, Taro, Chopra, Sumit, Cho, Kyunghyun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913599345131520
author Madaan, Divyam
Makino, Taro
Chopra, Sumit
Cho, Kyunghyun
author_facet Madaan, Divyam
Makino, Taro
Chopra, Sumit
Cho, Kyunghyun
contents Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the target as a source of multiple modalities and the interaction between them. Towards that end, we propose inter- & intra-modality modeling (I2M2) framework, which captures and integrates both the inter- and intra-modality dependencies, leading to more accurate predictions. We evaluate our approach using real-world healthcare and vision-and-language datasets with state-of-the-art models, demonstrating superior performance over traditional methods focusing only on one type of modality dependency.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17613
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
Madaan, Divyam
Makino, Taro
Chopra, Sumit
Cho, Kyunghyun
Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the target as a source of multiple modalities and the interaction between them. Towards that end, we propose inter- & intra-modality modeling (I2M2) framework, which captures and integrates both the inter- and intra-modality dependencies, leading to more accurate predictions. We evaluate our approach using real-world healthcare and vision-and-language datasets with state-of-the-art models, demonstrating superior performance over traditional methods focusing only on one type of modality dependency.
title Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
topic Computer Vision and Pattern Recognition
Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.17613