AI Paper Atlas

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

Monocular 3D Object Detection via Feature Domain Adaptation

Xiaoqing Ye, Liang Du, Yifeng Shi, Yingying Li, Xiao Tan, Jianfeng Feng, Errui Ding, Shilei Wen

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 45 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 feature domain adaptation (pseudo-LiDAR to LiDAR features) (ablation)baseline · KITTI val Car ModerateAP3D: 21.9 -> 23.1Improved
add supervised foreground segmentation loss (ablation)baseline without DA · KITTI val Car ModerateAP3D: 15.7 -> 21.9Improved
add context-aware foreground segmentation (CAFS) (ablation)baseline without DA · KITTI val Car ModerateAP3D: 21.9 -> 22.4Improved
replace supervised segmentation loss with CAFS (ablation)DA model · KITTI val Car ModerateAP3D: 23.1 -> 23.6Improved
add foreground segmentation supervision/CAFS over unsupervised segmentation (ablation)DA model · KITTI val Car ModerateAP3D: 16.1 -> 23.6Improved
use two-branch decoder (xyzr, whl) instead of one (ablation)DA + CAFS · KITTI val Car ModerateAP3D: 23.6 -> 24.0Improved
use three-branch decoder instead of two (ablation)DA + CAFS · KITTI val Car ModerateAP3D: 24.0 -> 23.2Hurt
two-branch decoder without DA (ablation)baseline · KITTI val Car ModerateAP3D: 21.9 -> 22.1Improved
use L2 instead of L1 adaptation loss (ablation)DA-3Ddet · KITTI val Car ModerateAP3D: 23.3 -> 24.0Improved
increase sampled points from 1024 (ablation)DA-3Ddet · KITTI val Car ModerateAP3D: 24.0 -> 23.8No clear effect
adapt mono features to LiDAR featuresMono pseudo-LiDAR · KITTI val Car ModerateAP3D: 21.9 -> 24.0Improved
adapt stereo features to LiDAR featuresStereo pseudo-LiDAR · KITTI val Car ModerateAP3D: 44.0 -> 46.1Improved

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