Research map / Detection and segmentation / CNN features
Label Decoupling Framework for 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 |
|---|---|---|---|
| Use label decoupling and feature interaction in LDF rather than the strongest listed baseline | LDF · ECSSD | MAE: .035 -> .034 | Helped |
| Use LDF rather than the strongest listed baseline | LDF · PASCAL-S | mF: .832 -> .848 | Helped |
| Use LDF rather than the strongest listed baseline | LDF · DUTS-TE | mF: .815 -> .855 | Helped |
| Use LDF rather than the strongest listed baseline | LDF · HKU-IS | MAE: .032 -> .027 | Helped |
| Use LDF rather than the strongest listed baseline | LDF · DUT-OMRON | mF: .756 -> .773 | Helped |
| Use LDF rather than the strongest listed baseline | LDF · THUR15K | mF: .741 -> .764 | Helped |
| Add one feature interaction rather than none (ablation) | LDF · THUR15K | mF: 0.751 -> 0.764 | Helped |
| Add one feature interaction rather than none (ablation) | LDF · DUTS-TE | mF: 0.839 -> 0.855 | Helped |
| Use two or three interactions instead of one (ablation) | LDF · THUR15K and DUTS-TE | mF: 0.764 -> 0.756; 0.764 -> 0.753; 0.855 -> 0.849; 0.855 -> 0.842 | Hurt |
| Use body and detail supervision instead of body and edge supervision (ablation) | LDF · THUR15K and DUTS-TE | mF: 0.758 -> 0.764; 0.850 -> 0.855 | Helped |
| Use body and detail supervision instead of saliency and detail supervision (ablation) | LDF · THUR15K and DUTS-TE | mF: 0.756 -> 0.764; 0.848 -> 0.855 | Helped |
Closest papers by meaning
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.89)
- Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR 2019 · similarity 0.87)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.87)
- F³Net: Fusion, Feedback and Focus for Salient Object Detection (AAAI 2020 · similarity 0.87)
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (AAAI 2021 · similarity 0.87)
- Salient Object Detection Driven by Fixation Prediction (CVPR 2018 · 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.