AI Paper Atlas

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

HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder

Yingqi Tang, Zhuoran Xu, Zhaotie Meng, Erkang Cheng

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 28 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 planning deformable attention to unified decoder without multi-granularity (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 41.3 -> 49.7Improved
add multi-granularity to unified decoder without planning deformable attention (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 41.3 -> 76.4Improved
add planning deformable attention on top of multi-granularity (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 76.4 -> 88.3Improved
use unified parallel decoder instead of sequential perception then planning (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 73.2 -> 88.3Improved
use unified parallel decoder instead of sequential perception then planning (ablation)HiP-AD · Bench2Drive 55-route subsetSuccess Rate (%): 45.5 -> 72.7Improved
add spatial waypoints to temporal waypoints (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 49.7 -> 53.6Improved
add granularity fusion (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 53.6 -> 62.4Improved
add align-matching (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 62.4 -> 79.5Improved
add align-matching (ablation)HiP-AD · Bench2Drive 55-route subsetSuccess Rate (%): 29.0 -> 56.3Improved
use 5Hz and 2m waypoints instead of 2Hz and 5m (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 79.5 -> 82.1Improved
combine dense and sparse sampling intervals (ablation)HiP-AD · Bench2Drive 55-route subsetDriving Score: 82.1 -> 84.2Improved
add driving-style waypoints (ablation)HiP-AD · Bench2Drive 55-route subsetSuccess Rate (%): 65.5 -> 72.7Improved

Later papers that compared with this method

4 later accepted papers report HiP-AD as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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