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

• URL: http://arxiv.org/abs/2409.07267v4
• Date: Wed, 20 Nov 2024 10:34:21 GMT
• Title: MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving
• Authors: Enming Zhang, Xingyuan Dai, Yisheng Lv, Qinghai Miao,
• Abstract summary: Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving. Most existing methods rely on computationally expensive visual encoders and large language models (LLMs) 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)
• Score: 10.74799483937468
• License:
• 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. 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.

Related papers

• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• PerspectiveNet: Multi-View Perception for Dynamic Scene Understanding [1.2781698000674653]
  PerspectiveNet is a lightweight model for generating long descriptions across multiple camera views. Our approach utilizes a vision encoder, a compact connector module, and large language models. The resulting model is lightweight, ensuring efficient training and inference, while remaining highly effective.
  arXiv  Detail & Related papers  (2024-10-22T08:57:17Z)
• EVLM: An Efficient Vision-Language Model for Visual Understanding [18.794601813330715]
  This paper proposes an efficient multi-modal language model to minimize computational costs. Our model achieves competitive scores on public multi-modal benchmarks and performs well in tasks such as image captioning and video captioning.
  arXiv  Detail & Related papers  (2024-07-19T10:09:51Z)
• VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks [89.24440488456405]
  VisionLLM v2 is an end-to-end generalist multimodal large model (MLLM) It unifies visual perception, understanding, and generation within a single framework.
  arXiv  Detail & Related papers  (2024-06-12T16:44:50Z)
• Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want [58.091825321168514]
  We introduce the Draw-and-Understand project: a new model, a multi-domain dataset, and a challenging benchmark for visual prompting. Specifically, we propose a new end-to-end trained Multimodal Large Language Model (MLLM) that connects a vision encoder, a visual prompt encoder and an LLM. To advance visual prompting research for MLLMs, we introduce MDVP-Data and MDVP-Bench.
  arXiv  Detail & Related papers  (2024-03-29T16:26:20Z)
• Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving [0.0]
  We develop an efficient, lightweight, multi-frame vision language model which performs Visual Question Answering for autonomous driving. In comparison to previous approaches, EM-VLM4AD requires at least 10 times less memory and floating point operations.
  arXiv  Detail & Related papers  (2024-03-28T21:18:33Z)
• Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model [83.85856356798531]
  VistaLLM is a visual system that addresses coarse- and fine-grained vision-language tasks. It employs a gradient-aware adaptive sampling technique to represent binary segmentation masks as sequences. We also introduce a novel task, AttCoSeg, which boosts the model's reasoning and grounding capability over multiple input images.
  arXiv  Detail & Related papers  (2023-12-19T18:53:01Z)
• MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning [65.60607895153692]
  MiniGPT-v2 is a model that can be treated as a unified interface for better handling various vision-language tasks. We propose using unique identifiers for different tasks when training the model. Our results show that MiniGPT-v2 achieves strong performance on many visual question-answering and visual grounding benchmarks.
  arXiv  Detail & Related papers  (2023-10-14T03:22:07Z)
• Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants [65.47222691674074]
  Muffin framework employs pre-trained vision-language models to act as providers of visual signals. UniMM-Chat dataset explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions.
  arXiv  Detail & Related papers  (2023-10-01T12:35:18Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.