Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives

TL;DR

This survey analyzes multi-modal multi-task foundation models for road scene understanding, emphasizing their learning paradigms, capabilities, challenges, and future directions in intelligent vehicle systems.

Contribution

It provides a comprehensive overview of MM-VUFMs for road scenes, highlighting recent practices, paradigms, and future research trends in the field.

Findings

MM-VUFMs effectively fuse multi-modal data for holistic scene understanding.

Advanced learning paradigms enhance adaptability and robustness of models.

Key challenges include interpretability and closed-loop system integration.

Abstract

Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems. In the context of intelligent vehicles, leveraging the power of foundation models has proven to be transformative, offering notable advancements in visual understanding. Equipped with multi-modal and multi-task learning capabilities, multi-modal multi-task visual understanding foundation models (MM-VUFMs) effectively process and fuse data from diverse modalities and simultaneously handle various driving-related tasks with powerful adaptability, contributing to a more holistic understanding of the surrounding scene. In this survey, we present a systematic analysis of MM-VUFMs specifically designed for road scenes. Our objective is not only to provide a comprehensive overview of common practices, referring to task-specific models, unified multi-modal models, unified multi-task models, and foundation model prompting techniques, but also to highlight their advanced capabilities in diverse learning paradigms. These paradigms include open-world understanding, efficient transfer for road scenes, continual learning, interactive and generative capability. Moreover, we provide insights into key challenges and future trends, such as closed-loop driving systems, interpretability, embodied driving agents, and world models. To facilitate researchers in staying abreast of the latest developments in MM-VUFMs for road scenes, we have established a continuously updated repository at https://github.com/rolsheng/MM-VUFM4DS