AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World

Jungho Kim, Jiyong Oh, Seunghoon Yu, Hongjae Shin, Donghyuk Kwak, Jun Won Choi

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 9 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
replace DiffusionDrive head with ProposalNet (ablation)SafeDrive · NAVSIM navtestPDMS: 88.6 -> 89.1Improved
add scene-level safety evaluation (ablation)ProposalNet · NAVSIM navtestPDMS: 89.1 -> 90.1Improved
add SWNet (ablation)ProposalNet + scene-level safety · NAVSIM navtestPDMS: 90.1 -> 90.9Improved
add FRNet without SWNet (ablation)ProposalNet + scene-level safety · NAVSIM navtestPDMS: 90.1 -> 90.9Improved
add both SWNet and FRNet (ablation)ProposalNet + scene-level safety · NAVSIM navtestPDMS: 90.9 -> 91.6Improved
use sparse world instead of BEV world with fine-grained safety (ablation)SafeDrive · NAVSIM navtestPDMS: 90.9 -> 91.6Improved
BEV world model without safety evaluation vs no world model (ablation)SafeDrive · NAVSIM navtestPDMS: 90.1 -> 90.3No clear effect
add PwNC head (ablation)FRNet · NAVSIM navtestPDMS: 90.9 -> 91.5Improved
add TwDAC head (ablation)FRNet · NAVSIM navtestPDMS: 90.9 -> 91.4Improved
add both PwNC and TwDAC (ablation)FRNet · NAVSIM navtestPDMS: 90.9 -> 91.6Improved
SafeDrive vs prior best on Bench2DriveSafeDrive · Bench2DriveDriving Score: 63.46 -> 66.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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