AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

Xiaoshuai Hao, Ruikai Li, Hui Zhang, Rong Yin, Dingzhe Li, Sangil Jung, Seung-In Park, ByungIn Yoo, Haimei Zhao, Jing Zhang

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 24 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 all three distillation losses (relation, feature, head) to camera-only student (ablation)MapTR ResNet18 student · nuScenes valmAP: 45.9 -> 53.6Improved
add cross-modal relation distillation alone (ablation)MapTR ResNet18 student · nuScenes valmAP: 45.9 -> 48.8Improved
add map head distillation alone (ablation)MapTR ResNet18 student · nuScenes valmAP: 45.9 -> 49.0Improved
add dual-level feature distillation alone (ablation)MapTR ResNet18 student · nuScenes valmAP: 45.9 -> 48.4Improved
combine the three distillation losses (vs best pair) (ablation)MapDistill · nuScenes valmAP: 51.1 -> 53.6Improved
use cross-modal relation distillation instead of uni-modal (ablation)MapDistill · nuScenes valmAP: 52.0 -> 53.6Improved
add uni-modal relation to cross-modal relation (hybrid) (ablation)MapDistill · nuScenes valmAP: 53.6 -> 52.4Hurt
use dual-level instead of low-level only feature distillation (ablation)MapDistill · nuScenes valmAP: 52.7 -> 53.6Improved
use both classification and point losses in map head distillation (ablation)MapDistill · nuScenes valmAP: 51.9 -> 53.6Improved
use dual BEV transform with different 2D-to-BEV methods (GKT and LSS) (ablation)student model · nuScenes valmAP: 49.1 -> 53.6Improved
use same 2D-to-BEV method in both dual BEV branches (ablation)student model · nuScenes valmAP: 49.1 -> 50.9Mixed
use camera-LiDAR fusion teacher instead of camera-only or LiDAR-only teacherMapDistill · nuScenes valmAP: 48.0 / 50.1 -> 53.6Improved

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