AI Paper Atlas

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

TAD-E2E: A Large-scale End-to-end Autonomous Driving Dataset

Chang Liu, Mingxu Zhu, Zheyuan Zhang, Linna Song, Xiao Zhao, Qingliang Luo, Qi Wang, Chufan Guo, Kuifeng Su

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 3 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 LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · nuScenesDetection mAP: 0.415 -> 0.618Improved
add LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · TAD-E2EDetection mAP: 0.226 -> 0.659Improved
add LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · TAD-E2EPlanning L2 avg (m): 1.63 -> 0.70Improved
add LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · TAD-E2EPlanning collision avg (%): 2.32 -> 0.45Improved
add LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · nuScenesPlanning collision avg (%): 0.14 -> 0.15No clear effect
add LiDAR to camera-only SparseDrive (SparseFusion-E2E)SparseDrive · nuScenesPlanning L2 avg (m): 0.69 -> 0.66No clear effect
evaluate on TAD-E2E instead of nuScenesSparseDrive · TAD-E2E vs nuScenesDetection mAP: 0.415 -> 0.226Hurt
evaluate on TAD-E2E instead of nuScenesUniAD · TAD-E2E vs nuScenesPlanning L2 avg (m): 0.73 -> 2.17Hurt
evaluate on TAD-E2E instead of nuScenesAD-MLP (ego state only) · TAD-E2E vs nuScenesPlanning L2 avg (m): 0.29 -> 4.37Hurt
evaluate on TAD-E2E instead of nuScenesSparseDrive · TAD-E2E vs nuScenesPlanning collision avg (%): 0.14 -> 2.32Hurt
evaluate on TAD-E2E instead of nuScenesSparseFusion-E2E · TAD-E2E vs nuScenesDetection mAP: 0.618 -> 0.659Improved

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