AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

DriveLM: Driving with Graph Visual Question Answering

Chonghao Sima, Katrin Renz, Kashyap Chitta, Li Chen, Zhang Hanxue, Chengen Xie, Jens Beißwenger, Ping Luo, Andreas Geiger, Hongyang Li

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 465 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add graph context (all P1-3 QAs) to behavior prediction (ablation)DriveLM-Agent · Waymo zero-shotbehavior speed accuracy: 43.90 -> 54.29Improved
use chain context (only P3) instead of full graph (ablation)DriveLM-Agent · Waymo zero-shotbehavior speed accuracy: 43.90 -> 41.28Hurt
add graph or chain context for behavior (ablation)DriveLM-Agent · DriveLM-nuScenes (in-domain)ADE: 1.39 (None) vs 1.74 (Graph)No clear effect
predict behavior as intermediate step before motionBLIP-RT-2 / DriveLM-Agent · DriveLM-nuScenesADE: 2.63 -> 1.39Improved
add prediction QA (P2-1) context to perception-only context (ablation)DriveLM-Agent behavior · DriveLM-nuScenesbehavior accuracy: 53.94 -> 58.82Improved
add planning QAs on top of prediction QAs (ablation)DriveLM-Agent behavior · DriveLM-nuScenesbehavior accuracy: 57.70 -> 58.95 (P3-1), 57.49 with allNo clear effect
add graph context to P1-3 QA (ablation)DriveLM-Agent · DriveLM-nuScenes P1-3SPICE: 42.56 -> 49.54Improved
add graph context to zero-shot BLIP-2 (ablation)BLIP-2 · DriveLM-CARLA P1-3GPT score: 46.37 -> 55.03Improved
add graph context to zero-shot BLIP-2 (ablation)BLIP-2 · DriveLM-CARLA P1-3SPICE: 10.46 -> 10.30No clear effect
fine-tune on DriveLM data vs zero-shot BLIP-2BLIP-2 · DriveLM-nuScenes P1-3GPT score: 42.97 -> 71.39Improved
use full graph context in Waymo zero-shot planning (ablation)DriveLM-Agent · Waymo zero-shotADE: 2.76 -> 2.63Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy