Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Video Salient Object Detection
Check 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 optical flow with the proposed appearance-motion fusion module (ablation) | B RGB-only baseline · DAVSOD | Fβ: 0.543 -> 0.562 | Helped |
| use proposed appearance-motion fusion instead of element-wise addition (ablation) | B-Fa · DAVSOD | Fβ: 0.556 -> 0.562 | Helped |
| use proposed appearance-motion fusion instead of concatenation (ablation) | B-Fc · FBMS | Fβ: +2% | Helped |
| add TIEM at every feature level rather than only the highest level (ablation) | B-Fo · DAVSOD | MAE: 0.121 -> 0.108 | Helped |
| add foreground-background similarity loss (ablation) | B-Fo-Ta · DAVSOD | Fβ: 0.585 -> 0.605 | Helped |
| use GraphCut to convert scribbles into training masks (ablation) | B · DAVSOD | Fβ: 0.543 -> 0.424 | Hurt |
| apply saliency boosting | Ours · DAVSOD | Fβ: 0.605 -> 0.593 | Hurt |
| apply saliency boosting | Ours · FBMS | Sα: 0.778 -> 0.803 | Helped |
| apply saliency boosting | Ours · DAVIS | Sα: 0.828 -> 0.846 | Helped |
| apply saliency boosting | Ours · VOS | Sα: 0.750 -> 0.765 | Helped |
| apply saliency boosting | Ours · SegV2 | Sα: 0.804 -> 0.819 | Helped |
| apply saliency boosting | Ours · ViSal | Sα: 0.857 -> 0.883 | Helped |
Closest papers by meaning
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (AAAI 2021 · similarity 0.93)
- Weakly-Supervised Salient Object Detection via Scribble Annotations (CVPR 2020 · similarity 0.91)
- Weakly-Supervised Salient Object Detection Using Point Supervision (AAAI 2022 · similarity 0.91)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.90)
- Learning to Detect Salient Objects With Image-Level Supervision (CVPR 2017 · similarity 0.89)
- Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection (NeurIPS 2021 · similarity 0.88)
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.