AI Paper Atlas

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

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

Han Lu, Xiaosong Jia, Yichen Xie, Siyu Sun, Wenlong Liao, Xiaokang Yang, Junchi Yan

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 27 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
use Ego-Diversity instead of random initial selection (10% data) (ablation)ActiveAD · nuScenes, VAD-TinyAverage collision (%): 0.67 -> 0.41Improved
add Soft Collision criterion to Displacement Error (ablation)ActiveAD incremental selection · nuScenes, 30% dataAverage collision (%): 0.35 -> 0.26Improved
use only Displacement Error for active selection (ablation)ActiveAD · nuScenesCollision rate / L2 at 30% vs 20%Mixed
add Agent Uncertainty criterion to DE and SC (ablation)ActiveAD · nuScenes, 30% dataAverage L2 (m): 0.73 -> 0.68Improved
add Agent Uncertainty criterion to DE and SC (ablation)ActiveAD · nuScenes, 30% dataAverage collision (%): 0.26 -> 0.21Improved
apply incremental selection on random initialization (ablation)random init baseline · nuScenes, 30% dataAverage L2 (m): 0.78 -> 0.71Improved
lower gamma from 1 to 0.5 in Ego-Diversity (more weight on minority scenes) (ablation)Ego-Diversity initialization · nuScenes, 10% initial dataL2 (m): 0.90 -> 0.83Improved
use gamma 0.8 rather than 0.5 (ablation)Ego-Diversity initialization · nuScenes, 10% initial dataCollision rate (%): 0.41 vs 0.43Mixed
use ActiveAD 30% selection instead of full-data trainingVAD-Tiny · nuScenes planningAverage L2 (m): 0.70 -> 0.68Improved
use ActiveAD with 30% data on CARLA instead of full dataVAD-Tiny · CARLA Town05 ShortDrive Score: 63.11 -> 63.24Improved
use general active learning baselines (Coreset, VAAL, KECOR, ActiveFT) instead of randomVAD-Tiny · nuScenes planningAverage L2 / collisionNo clear effect
increase data from 30% to 40-50%ActiveAD · nuScenes planningplanning performanceNo clear effect

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