MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving

20 Sept 2024 (modified: 13 Nov 2024)ICLR 2025 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Vision-language models, Autonomous driving
Abstract: Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel framework called MiniDrive, which incorporates our proposed Feature Engineering Mixture of Experts (FE-MoE) module and Dynamic Instruction Adapter (DI-Adapter). The FE-MoE effectively maps 2D features into visual token embeddings before being input into the language model. The DI-Adapter enables the visual token embeddings to dynamically change with the instruction text embeddings, resolving the issue of static visual token embeddings for the same image in previous approaches. The DI-Adapter enables the FE-MoE to further extract and process 2D visual features based on user instructions, focus on attention regions, and reduce redundancy. Compared to previous works, MiniDrive achieves state-of-the-art performance in terms of parameter size, floating point operations, and response efficiency, with the smallest version containing only 83M parameters.
Primary Area: applications to robotics, autonomy, planning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2084
Loading