Research map / Detection and segmentation / CNN features
Salient Object Detection: A Discriminative Regional Feature Integration Approach
Jingdong Wang, Huaizu Jiang, Zejian Yuan, Ming-Ming Cheng, Xiaowei Hu, Nanning Zheng
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 multi-level segmentation fusion to single-level DRFIs (ablation) | DRFI · MSRA-B | AUC: +1.22% | Improved |
| add multi-level segmentation fusion to single-level DRFIs (ablation) | DRFI · DUT-OMRON | AUC: +1.78% | Improved |
| use more segmentation layers at test time (ablation) | DRFI · cross-validation on training set | AUC | Improved |
| use more training segmentations Mt (ablation) | DRFI Random Forest · cross-validation on training set | AUC | Improved |
| use more decision trees (ablation) | DRFI Random Forest · cross-validation on training set | AUC | Improved |
| increase number of randomly chosen split features m up to all features (ablation) | DRFI Random Forest · cross-validation on training set | AUC | Hurt |
| use only the top 60 features instead of all 93 (ablation) | DRFI · MSRA-B and other benchmarks | AUC | No clear effect |
| add backgroundness descriptor (ablation) | DRFI · ECSSD | AUC | Hurt |
| add regional contrast descriptor (ablation) | DRFI · most benchmarks | AUC | No clear effect |
| add regional property descriptor (ablation) | DRFI · MSRA-B, ECSSD, DUT-OMRON | AUC | Improved |
| learn feature integration with Random Forest instead of heuristic combination | salient object detection · five benchmarks | AUC: +1.57% MSRA-B, +3.45% DUT-OMRON | Improved |
Closest papers by meaning
- Instance-Level Salient Object Segmentation (CVPR 2017 · similarity 0.92)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.92)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.92)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.91)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.91)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · similarity 0.91)
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.
