AI Paper Atlas

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

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

Cheng-Ju Ho, Chen-Hsuan Tai, Yen-Yu Lin, Ming-Hsuan Yang, Yi-Hsuan Tsai

NeurIPS 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 6 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 3DIoUMatch with Diffusion-SS3D3D semi-supervised object detection · ScanNet val, 5% labeledmAP@0.5: 5.4↑Improved
Replace 3DIoUMatch with Diffusion-SS3D3D semi-supervised object detection · SUN RGB-D val, 1% labeledmAP@0.5: 6.7↑Improved
Add diffusion denoising for object sizes (ablation)Diffusion-SS3D · ScanNet 5% labeledmAP@0.5: 22.8 ± 0.8 -> 26.3 ± 0.2Improved
Add diffusion denoising for object sizes (ablation)Diffusion-SS3D · SUN RGB-D 1% labeledmAP@0.5: 8.0 ± 1.5 -> 13.8 ± 0.7Improved
Add diffusion denoising for class labels (ablation)Diffusion-SS3D · ScanNet 5% labeledmAP@0.5: 22.8 ± 0.8 -> 26.0 ± 0.5Improved
Add diffusion denoising for class labels (ablation)Diffusion-SS3D · SUN RGB-D 1% labeledmAP@0.5: 8.0 ± 1.5 -> 13.3 ± 0.2Improved
Use both size and label diffusion (ablation)Diffusion-SS3D · ScanNet 5% labeledmAP@0.5: 26.3 ± 0.2 -> 27.9 ± 0.3Improved
Use both size and label diffusion (ablation)Diffusion-SS3D · SUN RGB-D 1% labeledmAP@0.5: 13.8 ± 0.7 -> 14.7 ± 1.2Improved
Add DDIM sampling (ablation)Diffusion-SS3D teacher pseudo-labeling · ScanNet 5% labeledmAP@0.5: 22.8 ± 0.8 -> 26.6 ± 0.9Improved
Add box renewal (ablation)Diffusion-SS3D teacher pseudo-labeling · SUN RGB-D 1% labeledmAP@0.5: 8.0 ± 1.5 -> 12.8 ± 0.6Improved
Increase DDIM sampling from 2 to 4 steps (ablation)Diffusion-SS3D · SUN RGB-D 1% labeledmAP@0.5: 14.7 ± 1.2 -> 12.9 ± 0.3Hurt
Increase DDIM sampling from 2 to 4 steps (ablation)Diffusion-SS3D · ScanNet 5% labeledmAP@0.25: 43.5 ± 0.2 -> 44.0 ± 1.1Mixed

Later papers that compared with this method

1 later accepted paper reports Diffusion-SS3D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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