AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Pseudo-SD: Pseudo Controlled Stable Diffusion for Semi-Supervised and Cross-Domain Semantic Segmentation

Dong Zhao, Qi Zang, Shuang Wang, Nicu Sebe, Zhun Zhong

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Consistency training for semi-supervised segmentation · 8 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 reliable pseudo-labels only for partial attention manipulation instead of all pseudo-labels (ablation)Pseudo-SD · Pascal (1/115)mIoU: 74.9 -> 79.1Improved
Use reliable pseudo-labels only for partial attention manipulation instead of all pseudo-labels (ablation)Pseudo-SD · COCO (1/512)mIoU: 34.6 -> 39.9Improved
Use reliable pseudo-labels only for partial attention manipulation instead of all pseudo-labels (ablation)Pseudo-SD · SFUDA G2CmIoU: 58.7 -> 62.7Improved
Replace ControlNet with partial attention manipulation for fine-tuning SD (ablation)Pseudo-SD · Pascal (1/115)mIoU: 70.9 -> 79.1Improved
Replace ControlNet with partial attention manipulation for fine-tuning SD (ablation)Pseudo-SD · SFUDA G2CmIoU: 51.5 -> 62.7Improved
Replace ControlNet with partial attention manipulation for fine-tuning SD (ablation)Pseudo-SD · UDA HRDAmIoU: 65.8 -> 76.9Improved
Fine-tune SD with ControlNet on pseudo-labels instead of no synthetic data (ablation)UniMatch / HRDA baselines · UDA HRDAmIoU: 75.8 -> 50.4Hurt
Add Connected Components Removal (ablation)Pseudo-SD · Pascal (1/115)mIoU: 74.9 -> 79.1Improved
Add Connected Components Removal (ablation)Pseudo-SD · SFUDA G2CmIoU: 56.7 -> 62.7Improved
Add Hard-Adapted Class Resampling (ablation)Pseudo-SD · Cityscapes (1/64)mIoU: 67.1 -> 69.8Improved
Add Hard-Adapted Class Resampling (ablation)Pseudo-SD · COCO (1/512)mIoU: 37.1 -> 39.9Improved
Use unsupervised-segmentation structured pseudo-labels (STEGO) directly to train segmenter (ablation)UniMatch · Pascal (1/115)mIoU: 75.2 -> 73.3Hurt

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