AI Paper Atlas

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

Decoupling Scene Perception and Ego Status: A Multi-Context Fusion Approach for Enhanced Generalization in End-to-End Autonomous Driving

Jiacheng Tang, Mingyue Feng, Jiachao Liu, Yaonong Wang, Jian Pu

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2 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 dual-branch decoupling and fusion (without auxiliary regularizers) (ablation)AdaptiveAD baseline · nuScenes valavg L2 (m): 0.57 -> 0.62Hurt
add dual-branch decoupling and fusion (without auxiliary regularizers) (ablation)AdaptiveAD baseline · nuScenes valavg collision rate (%): 0.22 -> 0.15Improved
add BEV unidirectional distillation (ablation)AdaptiveAD · nuScenes valavg collision rate (%): 0.15 -> 0.08Improved
add BEV unidirectional distillation (ablation)AdaptiveAD · nuScenes valavg L2 (m): 0.62 -> 0.58Improved
add scene-aware initialization of fusion query (ablation)AdaptiveAD · nuScenes valavg L2 (m): 0.58 -> 0.52Improved
add autoregressive online mapping (ablation)AdaptiveAD · nuScenes valavg L2 (m): 0.52 -> 0.47Improved
add autoregressive online mapping (ablation)AdaptiveAD · nuScenes valavg collision rate (%): 0.12 -> 0.12No clear effect
replace deformable attention with path attention (ablation)AdaptiveAD · nuScenes valavg collision rate (%): 0.15 -> 0.12Improved
add path attention plug-inUniAD · nuScenes valavg L2 (m): 0.73 -> 0.68Improved
add autoregressive online mapping plug-inSparseDrive · nuScenes valavg L2 (m): 0.58 -> 0.53Improved
add autoregressive online mapping plug-inSparseDrive · nuScenes valavg collision rate (%): 0.06 -> 0.06No clear effect
use AdaptiveAD instead of VAD under zeroed ego velocityAdaptiveAD vs VAD · nuScenes valavg L2 (m): 5.54 -> 4.08Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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