MTA: Multimodal Task Alignment for BEV Perception and Captioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Yunsheng, Yaman, Burhaneddin, Ye, Xin, Luo, Jingru, Tao, Feng, Mallik, Abhirup, Wang, Ziran, Ren, Liu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915190443868160
author Ma, Yunsheng
Yaman, Burhaneddin
Ye, Xin
Luo, Jingru
Tao, Feng
Mallik, Abhirup
Wang, Ziran
Ren, Liu
author_facet Ma, Yunsheng
Yaman, Burhaneddin
Ye, Xin
Luo, Jingru
Tao, Feng
Mallik, Abhirup
Wang, Ziran
Ren, Liu
contents Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment. However, existing approaches treat perception and captioning as separate tasks, focusing on the performance of only one task and overlooking the potential benefits of multimodal alignment. To bridge this gap between modalities, we introduce MTA, a novel multimodal task alignment framework that boosts both BEV perception and captioning. MTA consists of two key components: (1) BEV-Language Alignment (BLA), a contextual learning mechanism that aligns the BEV scene representations with ground-truth language representations, and (2) Detection-Captioning Alignment (DCA), a cross-modal prompting mechanism that aligns detection and captioning outputs. MTA seamlessly integrates into state-of-the-art baselines during training, adding no extra computational complexity at runtime. Extensive experiments on the nuScenes and TOD3Cap datasets show that MTA significantly outperforms state-of-the-art baselines in both tasks, achieving a 10.7% improvement in challenging rare perception scenarios and a 9.2% improvement in captioning. These results underscore the effectiveness of unified alignment in reconciling BEV-based perception and captioning.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10639
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MTA: Multimodal Task Alignment for BEV Perception and Captioning
Ma, Yunsheng
Yaman, Burhaneddin
Ye, Xin
Luo, Jingru
Tao, Feng
Mallik, Abhirup
Wang, Ziran
Ren, Liu
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
Bird's eye view (BEV)-based 3D perception plays a crucial role in autonomous driving applications. The rise of large language models has spurred interest in BEV-based captioning to understand object behavior in the surrounding environment. However, existing approaches treat perception and captioning as separate tasks, focusing on the performance of only one task and overlooking the potential benefits of multimodal alignment. To bridge this gap between modalities, we introduce MTA, a novel multimodal task alignment framework that boosts both BEV perception and captioning. MTA consists of two key components: (1) BEV-Language Alignment (BLA), a contextual learning mechanism that aligns the BEV scene representations with ground-truth language representations, and (2) Detection-Captioning Alignment (DCA), a cross-modal prompting mechanism that aligns detection and captioning outputs. MTA seamlessly integrates into state-of-the-art baselines during training, adding no extra computational complexity at runtime. Extensive experiments on the nuScenes and TOD3Cap datasets show that MTA significantly outperforms state-of-the-art baselines in both tasks, achieving a 10.7% improvement in challenging rare perception scenarios and a 9.2% improvement in captioning. These results underscore the effectiveness of unified alignment in reconciling BEV-based perception and captioning.
title MTA: Multimodal Task Alignment for BEV Perception and Captioning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.10639