AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection

Chuxin Wang, Wenfei Yang, Tianzhu Zhang

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 11 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
replace deterministic box parameterization with side-aware parameterization alone (ablation)VoteNet semi-supervised · ScanNet 20%mAP50: 30.12 -> 30.42No clear effect
add soft pseudo-label selection using distribution variance (ablation)VoteNet semi-supervised · ScanNet 20%mAP50: 30.42 -> 33.28Improved
add side-aware uncertainty estimation module with geometric and distribution features (ablation)VoteNet semi-supervised · ScanNet 20%mAP50: 33.28 -> 37.29Improved
combine geometric features with distribution properties instead of either alone (ablation)Uncertainty estimation module · ScanNet 20%mAP50: 36.41 -> 37.29Improved
use side-aware parameterization instead of naive center/size parameterization (ablation)VoteNet semi-supervised · ScanNet 20%mAP50: 32.66 -> 37.29Improved
make regression probabilistic with side-aware parameterization (ablation)VoteNet semi-supervised · ScanNet 20%mAP50: 35.02 -> 37.29Improved
add side-aware weight assignment (ablation)Soft-PLS · ScanNet 20%mAP50: 35.79 -> 37.29Improved
add category-specific adaptive thresholds (ablation)Soft-PLS · ScanNet 20%mAP50: 35.21 -> 35.79Improved
add IoU-guided NMS with low-half strategy (ablation)Soft-PLS · ScanNet 20%mAP50: 30.42 -> 35.21Improved
raise pseudo-label thresholds to higher values (ablation)Soft-PLS · ScanNet 20%mAP50: 37.29 -> 34.73Hurt
lower pseudo-label thresholds (ablation)Soft-PLS · ScanNet 20%mAP50: 37.29 -> 36.91No clear effect
apply the method with 100% labeled data (copy as unlabeled)VoteNet · ScanNet 100%mAP50: 36.0 -> 44.1Improved

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