Research map / Detection and segmentation / Weakly supervised detection and segmentation
Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence
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 |
|---|---|---|---|
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · ECSSD | Fβ: 0.8650 -> 0.8995 | Helped |
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · DUT-OMRON | Fβ: 0.7015 -> 0.7580 | Helped |
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · PASCAL-S | Fβ: 0.7884 -> 0.8230 | Helped |
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · HKU-IS | Fβ: 0.8576 -> 0.8962 | Helped |
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · THUR | Fβ: 0.7181 -> 0.7545 | Helped |
| Use SCWSSOD instead of WSSA† | scribble-supervised salient object detection · DUTS-TEST | Fβ: 0.7467 -> 0.8226 | Helped |
| Add local saliency coherence loss (ablation) | SCWSSOD with scribble supervision · DUTS-TEST | Fβ: 0.7584 -> 0.8226 | Helped |
| Add saliency structure consistency loss (ablation) | GCPANet with AGGM and partial cross entropy · DUTS-TEST | Fβ: 0.707 -> 0.758 | Helped |
| Add SSIM to saliency structure consistency loss (ablation) | SCWSSOD with AGGM · DUT-OMRON | Fβ: 0.670 -> 0.708 | Helped |
| Add AGGM (ablation) | SCWSSOD with all losses · DUT-OMRON | Fβ: 0.730 -> 0.758 | Helped |
| Add AGGM (ablation) | SCWSSOD with all losses · DUTS-TEST | Fβ: 0.800 -> 0.823 | Helped |
| Add AGGM without the proposed losses (ablation) | GCPANet trained with partial cross entropy · DUTS-TEST | Fβ: 0.707 -> 0.706 | No clear effect |
Closest papers by meaning
- Weakly-Supervised Salient Object Detection via Scribble Annotations (CVPR 2020 · similarity 0.96)
- Weakly-Supervised Salient Object Detection Using Point Supervision (AAAI 2022 · similarity 0.94)
- Weakly Supervised Video Salient Object Detection (CVPR 2021 · similarity 0.93)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.92)
- WeakPCSOD: Overcoming the Bias of Box Annotations for Weakly Supervised Point Cloud Salient Object Detection (AAAI 2024 · similarity 0.88)
- Unsupervised Salient Instance Detection (CVPR 2024 · 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.