AI Paper Atlas

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

End-to-End Autonomous Driving Without Costly Modularization and 3D Manual Annotation

Mingzhe Guo, Zhipeng Zhang, Yuan He, Ke Wang, Liping Jing, Haibin Ling

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 30 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 spatial objectness loss (ablation)UAD · nuScenes (NoAvg)avg L2 / collision: 3.18m -> 1.00m L2; 2.43% -> 0.71% collisionImproved
add circular update in dreaming decoder (ablation)UAD · nuScenes (NoAvg)avg L2: 1.82 -> 1.12Improved
add dreaming loss (ablation)UAD · nuScenes (NoAvg)avg L2: 1.82 -> 1.04Improved
add directional augmentation (ablation)UAD · nuScenes (NoAvg)avg L2: 0.97 -> 0.92Improved
add directional consistency (ablation)UAD · nuScenes (NoAvg)avg collision: 0.32 -> 0.19Improved
add angular design (partition and angular queries) (ablation)UAD · nuScenes (NoAvg)avg L2 / collision: 1.37 -> 0.90 L2; 1.37 -> 0.19 collisionImproved
add 3D detection head (ablation)UAD · nuScenes (NoAvg)avg L2 / collision: 0.90 -> 0.93 L2; 0.19 -> 0.25 collisionNo clear effect
use ImageNet pretraining for Res101 (ablation)UAD · nuScenes (NoAvg)avg L2: 0.95 -> 0.91Improved
use NuImages pretraining instead of none for Res101 (ablation)UAD · nuScenes (NoAvg)avg collision: 0.28 -> 0.19Improved
use GT 2D boxes instead of GroundingDINO pseudo ROIs (Res101) (ablation)UAD · nuScenes (NoAvg)avg L2: 0.90 -> 0.84Improved
use GT 2D boxes instead of pseudo ROIs (Res50) (ablation)UAD · nuScenes (NoAvg)avg L2: 0.99 -> 0.96Improved
decrease partition angle from 4 to 1 degree (ablation)UAD · nuScenes (NoAvg)avg L2 / collision: 0.90 -> 0.85 L2; 0.19 -> 0.32 collision, FPS 7.2 -> 5.0Mixed

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