Research map / Detection and segmentation / Open-set and few-shot detection
Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| add target-domain pseudo-label training to source-only training (ablation) | SYNSOD-trained LDF · DUTS-TE | S-measure: .802 -> .818 | Helped |
| add uncertainty-aware pseudo-label learning (ISS and PPR) to vanilla pseudo-label training (ablation) | LDF trained on SYNSOD and target pseudo-labels · DUTS-TE | S-measure: .818 -> .846 | Helped |
| add image-level sample selection (ISS) (ablation) | UPL · DUTS-TE | S-measure: .823 -> .846 | Helped |
| add pixel-wise pseudo-label reweighting (PPR) (ablation) | UPL · DUTS-TE | S-measure: .842 -> .846 | Helped |
| combine horizontal flip, scaling, and FDA augmentations for uncertainty estimation rather than using Flip alone (ablation) | UPL · DUTS-TE | weighted F-measure: .777 -> .783 | Helped |
| combine horizontal flip, scaling, and FDA augmentations for uncertainty estimation rather than using Flip alone (ablation) | UPL · ECSSD | weighted F-measure: .879 -> .885 | Helped |
| combine horizontal flip, scaling, and FDA augmentations for uncertainty estimation rather than using Flip alone (ablation) | UPL · DUT-O | weighted F-measure: .697 -> .711 | Helped |
| combine horizontal flip, scaling, and FDA augmentations for uncertainty estimation rather than using Flip alone (ablation) | UPL · HKU-IS | weighted F-measure: .875 -> .879 | Helped |
| use the proposed UDASOD method instead of EDNL | deep unsupervised SOD · DUTS-TE | S-measure: .820 -> .846 | Helped |
| use the proposed UDASOD method instead of EDNL | deep unsupervised SOD · ECSSD | S-measure: .871 -> .899 | Helped |
| use the proposed UDASOD method instead of EDNL | deep unsupervised SOD · DUT-O | S-measure: .783 -> .808 | Helped |
| use the proposed UDASOD method instead of EDNL | deep unsupervised SOD · HKU-IS | S-measure: .884 -> .897 | Helped |
Closest papers by meaning
- DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision (NeurIPS 2019 · similarity 0.92)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.91)
- Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection (CVPR 2022 · similarity 0.91)
- Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection (CVPR 2023 · similarity 0.90)
- Unsupervised Salient Instance Detection (CVPR 2024 · similarity 0.87)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.87)
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.