AI Paper Atlas

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

Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency

Qing Lian, Yanbo Xu, Weilong Yao, Yingcong Chen, Tong Zhang

ECCV 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 13 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 box-level consistency regularization (ablation)MVC-MonoDet (stereo) · KITTI val Car 100%3D AP Moderate: 16.32 -> 17.56Improved
add object-level consistency regularization (ablation)MVC-MonoDet (stereo) · KITTI val Car 100%3D AP Moderate: 16.32 -> 17.85Improved
combine box-level and object-level regularization (ablation)MVC-MonoDet (stereo) · KITTI val Car 100%3D AP Moderate: 17.85 -> 18.63Improved
add box-level consistency regularization (ablation)MVC-MonoDet (video) · KITTI val Car 100%3D AP Moderate: 16.32 -> 17.01Improved
add object-level consistency regularization (ablation)MVC-MonoDet (video) · KITTI val Car 100%3D AP Moderate: 16.32 -> 16.75Mixed
combine box-level and object-level regularization (ablation)MVC-MonoDet (video) · KITTI val Car 100%3D AP Moderate: 17.01 -> 17.34Improved
use stereo instead of video as unlabeled multi-view data (ablation)MVC-MonoDet · KITTI val Car 100%3D AP Moderate: 17.34 -> 18.63Improved
add semi-supervised multi-view consistency instead of multi-task depth supervision (ablation)Baseline detector (stereo) · KITTI val Car 100%3D AP Moderate: 17.21 -> 18.63Improved
use 10% labeled data with consistency regularization (ablation)MVC-MonoDet (video) · KITTI val Car 10%3D AP Moderate: 7.25 -> 7.96No clear effect
add MVC-MonoDet semi-supervised training with stereo (ablation)Baseline · KITTI val Car 50% vs 100% labeled3D AP Moderate: 16.40 vs 16.32Improved
add MVC-MonoDet video training on nuScenes (ablation)Baseline · nuScenes val 10% labeledmAP: 15.9 -> 18.8Improved
add MVC-MonoDet video training on nuScenes (ablation)Baseline · nuScenes val 100% labeledmAP: 33.2 -> 34.9Improved

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