Research map / Detection and segmentation / CNN features
Scene Context-Aware Salient Object Detection
Avishek Siris, Jianbo Jiao, Gary K.L. Tam, Xianghua Xie, Rynson W.H. Lau
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 Instance/Stuff context segmentation (ISCG) to Mask-RCNN base (ablation) | Mask-RCNN saliency baseline · Proposed dataset | avgF: 0.826 -> 0.841 | Improved |
| add Instance/Stuff context segmentation (ISCG) to Mask-RCNN base (ablation) | Mask-RCNN saliency baseline · Proposed dataset | MAE: 0.069 -> 0.063 | Improved |
| add SSCR module on top of Base+ISCG (ablation) | Base+ISCG · Proposed dataset | avgF: 0.841 -> 0.845 | Improved |
| add SSCR module on top of Base+ISCG (ablation) | Base+ISCG · Proposed dataset | E-measure: 0.866 -> 0.869 | Improved |
| add CIT on top of Base+ISCG (ablation) | Base+ISCG · Proposed dataset | avgF: 0.841 -> 0.849 | Improved |
| add CIT on top of Base+ISCG (ablation) | Base+ISCG · Proposed dataset | MAE: 0.063 -> 0.062 | Improved |
| add SSCR to Base+ISCG+CIT (full model) (ablation) | Base+ISCG+CIT · Proposed dataset | avgF: 0.849 -> 0.849 | No clear effect |
| add SSCR to Base+ISCG+CIT (full model) (ablation) | Base+ISCG+CIT · Proposed dataset | E-measure: 0.871 -> 0.872 | Improved |
| add CIT to Base+ISCG+SSCR (ablation) | Base+ISCG+SSCR · Proposed dataset | avgF: 0.845 -> 0.849 | Improved |
| full model versus second-best prior method (EGNet) on avgF | Scene-context saliency model · Proposed dataset | avgF: 0.815 -> 0.849 | Improved |
| full model versus Mask-RCNN base (ablation) | Mask-RCNN saliency baseline · Proposed dataset | MAE: 0.069 -> 0.062 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- EGNet — EGNet: Edge Guidance Network for Salient Object Detection (ICCV 2019) · better on 3 of 3 shared results
- BASNet — BASNet: Boundary-Aware Salient Object Detection (CVPR 2019) · better on 2 of 2 shared results
- S4Net — S4Net: Single Stage Salient-Instance Segmentation (CVPR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · similarity 0.91)
- Breaking Barriers, Localizing Saliency: A Large-Scale Benchmark and Baseline for Condition-Constrained Salient Object Detection (TPAMI 2025 · similarity 0.91)
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (ECCV 2018 · similarity 0.90)
- Salient Objects in Clutter (TPAMI 2022 · similarity 0.90)
- Inferring Salient Objects from Human Fixations (TPAMI 2019 · similarity 0.90)
- CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection (CVPR 2019 · similarity 0.90)
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.
