Research map / Detection and segmentation / Weakly supervised detection and segmentation
Semi-Supervised Video Salient Object Detection Based on Uncertainty-Guided Pseudo Labels
Yongri Piao, Chenyang Lu, Miao Zhang, Huchuan Lu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add CFGMM without adjacent GT reference (CFGMM-O) (ablation) | Pseudo label generator · DAVIS train pseudo labels | MAE: 0.016 -> 0.015 | Improved |
| add CFGMM with adjacent ground truth reference (ablation) | Pseudo label generator · DAVIS train pseudo labels | MAE: 0.016 -> 0.012 | Improved |
| add UADDM on top of CFGMM (ablation) | Pseudo label generator · DAVIS train pseudo labels | MAE: 0.012 -> 0.007 | Improved |
| add CFGMM to baseline (ablation) | Saliency model · DAVIS | MAE: 0.030 -> 0.028 | Improved |
| add UADDM on top of CFGMM (ablation) | Saliency model · DAVIS | MAE: 0.028 -> 0.024 | Improved |
| add ordinary GAN (ablation) | Saliency model · DAVIS | MAE: 0.024 -> 0.019 | Improved |
| replace ordinary GAN with noise-suppressed GAN (ablation) | Saliency model · DAVIS | MAE: 0.019 -> 0.019 | No clear effect |
| replace ordinary GAN with noise-suppressed GAN (ablation) | Saliency model · MCL | MAE: 0.019 -> 0.018 | Improved |
| use RGB, flow and fused output streams (ROF) instead of fused only (F) (ablation) | Generator · DAVIS | MAE: 0.043 -> 0.033 | Improved |
| increase pseudo labels from 0% to 50% (configuration M) (ablation) | Ours · DAVIS | MAE: 0.034 -> 0.019 | Improved |
| increase pseudo labels from 50% to 100% (configuration M) (ablation) | Ours · DAVIS | MAE: 0.019 -> 0.020 | No clear effect |
| increase pseudo labels from 50% to 100% (configuration M) (ablation) | Ours · FBMS | MAE: 0.027 -> 0.031 | Hurt |
Closest papers by meaning
- Semi-Supervised Video Salient Object Detection Using Pseudo-Labels (ICCV 2019 · similarity 0.92)
- Rethinking Pseudo Labels for Semi-supervised Object Detection (AAAI 2022 · similarity 0.89)
- Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection (AAAI 2023 · similarity 0.89)
- Learning from Noisy Data for Semi-Supervised 3D Object Detection (ICCV 2023 · similarity 0.88)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (CVPR 2024 · similarity 0.87)
- Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection (CVPR 2024 · similarity 0.86)
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.
