AI Paper Atlas

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

UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes

Sunwook Hwang, Youngseok Kim, Seongwon Kim, Saewoong Bahk, Hyung-Sin Kim

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 5 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
use feature-level ground-truth sampling instead of feature-level flip (ablation)UpCycling · KITTI partial-label (10% labeled), SECOND-IoUAP3D Mod gain over baseline: -20.09 -> +7.87Improved
add feature-level noise or random sampling instead of GT sampling (ablation)UpCycling · KITTI partial-label (10% labeled), SECOND-IoUAP3D: +0.03 / +0.13 / -1.23 (Noise); +2.47 / -0.96 / +0.63 (RS)No clear effect
combine feature-level Flip and RS (F-3DIoUMatch) (ablation)3DIoUMatch at feature level · KITTI partial-label (10% labeled), SECOND-IoUAP3D: -11.69 / -13.75 / -13.32Hurt
use feature-level GT sampling instead of feature-level rotation (ablation)UpCycling · KITTI partial-label (10% labeled), SECOND-IoUAP3D Hard gain over baseline: +7.96 -> +8.14Improved
apply UpCycling on features without Statistical Normalization for Waymo-to-KITTI adaptationUpCycling · Waymo to KITTI domain adaptationAP3D: 11.71 vs ST3D 40.16 (SECOND-IoU)Hurt
combine UpCycling with statistical normalization (SN)UpCycling · Waymo to KITTI domain adaptationAP3D: 11.71 -> 67.65 (SECOND-IoU)Improved
UpCycling versus ST3D on Waymo to LyftUpCycling · Waymo to Lyft domain adaptationAP3D: 29.90 -> 45.66 (SECOND-IoU)Improved
UpCycling versus 3DIoUMatch with 25% labelsUpCycling · KITTI partial-label (25% labeled)AP3DImproved
train the backbone with unlabeled raw data (raw-level UpCycling) instead of freezing it (ablation)UpCycling · KITTI partial-labelAP3DImproved

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