Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912935905853440 |
|---|---|
| author | Xiong, Minhao Wen, Zichen Gu, Zhuangcheng Liu, Xuyang Zhang, Rui Kang, Hengrui Yang, Jiabing Zhang, Junyuan Li, Weijia He, Conghui Wang, Yafei Zhang, Linfeng |
| author_facet | Xiong, Minhao Wen, Zichen Gu, Zhuangcheng Liu, Xuyang Zhang, Rui Kang, Hengrui Yang, Jiabing Zhang, Junyuan Li, Weijia He, Conghui Wang, Yafei Zhang, Linfeng |
| contents | Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13305 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving Xiong, Minhao Wen, Zichen Gu, Zhuangcheng Liu, Xuyang Zhang, Rui Kang, Hengrui Yang, Jiabing Zhang, Junyuan Li, Weijia He, Conghui Wang, Yafei Zhang, Linfeng Computer Vision and Pattern Recognition Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git |
| title | Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.13305 |