AI Paper Atlas

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

Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection

Yu Hong, Hang Dai, Yong Ding

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 99 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 depth pre-training of the backbone (ablation)CMKD · KITTI val Car Moderate3D AP: 8.52 -> 13.48Improved
add response distillation (ablation)CMKD · KITTI val Car Moderate3D AP: 13.48 -> 14.49Improved
add feature distillation (ablation)CMKD · KITTI val Car Moderate3D AP: 13.48 -> 15.46Improved
add both distillation modules (ablation)CMKD · KITTI val Car Moderate3D AP: 13.48 -> 16.33Improved
add unlabeled data distillation (ablation)CMKD · KITTI val Car Moderate3D AP: 16.33 -> 21.54Improved
add feature distillation loss L_feat (ablation)CMKD · KITTI val Car Easy3D AP: 18.81 -> 21.72Improved
add domain adaptation module (ablation)CMKD · KITTI val Car Easy3D AP: 21.72 -> 23.53Improved
add IoU-aware confidence weighting to response distillation (ablation)CMKD · KITTI val Car Moderate (KITTI train)3D AP: 15.69 -> 16.33Improved
use feature distillation instead of depth supervision with small training set (ablation)CMKD · KITTI val Car Moderate (KITTI train)3D AP: 15.20 -> 13.04Hurt
use feature distillation instead of depth supervision with larger training set (ablation)CMKD · KITTI val Car Moderate (KITTI train + Eigen clean)3D AP: 19.76 -> 21.32Improved
add depth supervision on top of feature distillation (larger set) (ablation)CMKD · KITTI val Car Moderate (KITTI train + Eigen clean)3D AP: 21.32 -> 21.53No clear effect
use soft labels instead of hard labels for Pedestrian (ablation)CMKD · KITTI val Pedestrian Moderate3D AP: 8.65 -> 3.20Hurt

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