AI Paper Atlas

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

LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection

Sanmin Kim, Youngseok Kim, Sihwan Hwang, Hyeonjun Jeong, Dongsuk Kum

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 22 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 feature and response distillation (ablation)BEVDepth ResNet50 · nuScenes valmAP: 33.6 -> 35.4Improved
add label distillation on top of LiDAR distillation (ablation)BEVDepth ResNet50 · nuScenes valmAP: 35.4 -> 37.0Improved
add feature partitioning on top of LiDAR + label distillation (ablation)BEVDepth ResNet50 · nuScenes valmAP: 37.0 -> 37.9Improved
train label encoder via inverse function approximation instead of plain AutoEncoder (ablation)LabelDistill · nuScenes valmAP: 34.9 -> 36.8Improved
train label encoder with student features (LabelEnc) instead of inverse function approximation (ablation)LabelDistill · nuScenes valmAP: 36.8 -> 34.8Hurt
use a more accurate label encoder (autoencoder mAP 50.2 to 94.1) (ablation)LabelDistill · nuScenes valstudent mAP: 34.0 -> 36.8Improved
use equal channel ratio for LiDAR, label and image groups (ablation)feature partitioning · nuScenes valmAP: 36.6 -> 37.6 (vs 1:3:2); 37.1 vs 3:1:2Improved
add label distillation for distant objects (over 30m) (ablation)LabelDistill · nuScenes val, objects beyond 30mmASE: 0.342 -> 0.270Improved
add label distillation for distant objects (over 30m) (ablation)LabelDistill · nuScenes val, objects beyond 30mmAOE: 0.534 -> 0.531No clear effect
apply LabelDistill to BEVDepth ConvNeXt-BBEVDepth · nuScenes testmAP: 47.5 -> 52.6Improved

Later papers that compared with this method

3 later accepted papers report LabelDistill as a baseline in their results tables; 3 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 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