AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Zhiqiang, Fang, Haoyang, Zhou, Su, Yang, Taojiannan, Zhong, Zihan, Hu, Tony, Kirchhoff, Katrin, Karypis, George
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910429143367680
author Tang, Zhiqiang
Fang, Haoyang
Zhou, Su
Yang, Taojiannan
Zhong, Zihan
Hu, Tony
Kirchhoff, Katrin
Karypis, George
author_facet Tang, Zhiqiang
Fang, Haoyang
Zhou, Su
Yang, Taojiannan
Zhong, Zihan
Hu, Tony
Kirchhoff, Katrin
Karypis, George
contents AutoGluon-Multimodal (AutoMM) is introduced as an open-source AutoML library designed specifically for multimodal learning. Distinguished by its exceptional ease of use, AutoMM enables fine-tuning of foundation models with just three lines of code. Supporting various modalities including image, text, and tabular data, both independently and in combination, the library offers a comprehensive suite of functionalities spanning classification, regression, object detection, semantic matching, and image segmentation. Experiments across diverse datasets and tasks showcases AutoMM's superior performance in basic classification and regression tasks compared to existing AutoML tools, while also demonstrating competitive results in advanced tasks, aligning with specialized toolboxes designed for such purposes.
format Preprint
id arxiv_https___arxiv_org_abs_2404_16233
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
Tang, Zhiqiang
Fang, Haoyang
Zhou, Su
Yang, Taojiannan
Zhong, Zihan
Hu, Tony
Kirchhoff, Katrin
Karypis, George
Machine Learning
Artificial Intelligence
AutoGluon-Multimodal (AutoMM) is introduced as an open-source AutoML library designed specifically for multimodal learning. Distinguished by its exceptional ease of use, AutoMM enables fine-tuning of foundation models with just three lines of code. Supporting various modalities including image, text, and tabular data, both independently and in combination, the library offers a comprehensive suite of functionalities spanning classification, regression, object detection, semantic matching, and image segmentation. Experiments across diverse datasets and tasks showcases AutoMM's superior performance in basic classification and regression tasks compared to existing AutoML tools, while also demonstrating competitive results in advanced tasks, aligning with specialized toolboxes designed for such purposes.
title AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.16233