AI Paper Atlas

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

ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection

Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

TPAMI 2022 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 69 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 random object scaling to source pre-training (ablation)source-only detector · Waymo->KITTI (car)AP_3D: 27.48 -> 54.67Improved
add random object scaling before self-training (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 33.73 -> 65.64Improved
add triplet box partition to naive self-training (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 65.88 -> 67.39Improved
add memory ensemble and voting (MEV-C) (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 67.39 -> 70.17Improved
use hybrid criterion instead of IoU-only criterion (QAC) (ablation)ST3D++ · Waymo->KITTI (pedestrian)AP_3D: 51.92 -> 56.13Improved
use hybrid criterion instead of IoU-only criterion (QAC) (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 72.52 -> 72.52No clear effect
add curriculum data augmentation (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 72.52 -> 73.37Improved
add source-assisted self-denoised training (SASD) (ablation)ST3D++ · Waymo->KITTI (car)AP_3D: 73.37 -> 74.61Improved
add source-assisted self-denoised training (SASD) (ablation)ST3D++ · Waymo->KITTI (cyclist)AP_3D: 53.49 -> 60.76Improved
add source-assisted self-denoised training (SASD) (ablation)ST3D++ · Waymo->KITTI (pedestrian)AP_3D: 56.27 -> 59.21Improved
add target object size prior (SN) to ST3D++ST3D++ · Waymo->KITTI (car)AP_3D: 65.64 -> 74.61Improved
add target object size prior (SN) to ST3D++ST3D++ · Waymo->Lyft (car)AP_3D: 59.93 -> 58.86Hurt

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