AI Paper Atlas

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

MonoDistill: Learning Spatial Features for Monocular 3D Object Detection

Zhiyu Chong, Xinzhu Ma, Hong Zhang, Yuxin Yue, Haojie Li, Zhihui Wang, Wanli Ouyang

ICLR 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 58 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
Distill spatial cues from an aligned LiDAR teacher into MonoDLEMonoDLE · KITTI test, Car 3D@IoU=0.7AP|R40: 12.26 -> 16.03Improved
Add scene-level feature distillation (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 15.13 -> 16.96Improved
Add object-level feature distillation (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 15.13 -> 16.85Improved
Add object-level result distillation (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 15.13 -> 17.24Improved
Combine scene-level, object-level feature, and object-level result distillation (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 15.13 -> 18.24Improved
Add attention-based feature fusion to the three distillation schemes (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 18.24 -> 18.47Improved
Restrict object-level feature distillation to foreground regions rather than the whole image (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 16.13 -> 16.85Improved
Use diffused region labels rather than sparse point labels for result distillation (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 15.51 -> 17.24Improved
Use LiDAR-guided knowledge distillation instead of direct dense-depth supervisionMonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 17.05 -> 18.47Improved
Use LiDAR rather than stereo depth to guide the teacher (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 18.18 -> 18.47Improved
Use dense rather than sparse LiDAR maps for teacher training (ablation)MonoDLE · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 18.07; 18.47No clear effect
Apply MonoDistill to GUPNetGUPNet · KITTI validation, Car 3D@IoU=0.7 moderateAP|R40: 16.46 -> 16.69Improved

Later papers that compared with this method

1 later accepted paper reports MonoDistill as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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