Research map / Detection and segmentation / CNN features
Salient Object Detection via Integrity Learning
Mingchen Zhuge, Deng-Ping Fan, Nian Liu, Dingwen Zhang, Dong Xu, Ling Shao
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 DFA to the baseline (ablation) | encoder-decoder baseline · DUTS-TE | weighted F-measure: 0.801 -> 0.818 | Improved |
| add ICE on top of DFA (ablation) | baseline+DFA · DUTS-TE | weighted F-measure: 0.818 -> 0.825 | Improved |
| add PWV on top of DFA+ICE (ablation) | baseline+DFA+ICE · DUTS-TE | weighted F-measure: 0.825 -> 0.836 | Improved |
| add all three modules to the baseline (ablation) | baseline · OMRON | MAE: 0.064 -> 0.057 | Improved |
| use DFA instead of Inception (ablation) | ICON · HKU-IS | weighted F-measure: 0.869 -> 0.875 | Improved |
| use DFA instead of ASPP/Inception/PSP in terms of MAE (ablation) | ICON · DUTS-TE | MAE: 0.043 -> 0.046 | Hurt |
| combine three different conv types in DFA rather than only 3xAtrConv (ablation) | DFA · DUTS-TE | weighted F-measure: 0.811 -> 0.818 | Improved |
| use 3xAsyConv instead of 3xOriConv in DFA (ablation) | DFA · DUTS-TE | weighted F-measure: 0.810 -> 0.817 | Improved |
| use ICE instead of SE (ablation) | DFA+ICE · OMRON | weighted F-measure: 0.720 -> 0.753 | Improved |
| use ICE instead of GCT (ablation) | DFA+ICE · OMRON | weighted F-measure: 0.712 -> 0.753 | Improved |
| use ICE instead of CBAM (ablation) | DFA+ICE · DUTS-TE | weighted F-measure: 0.832 -> 0.825 | No clear effect |
| use EM routing instead of self-routing (ablation) | PWV · HKU-IS | E-measure: 0.843 -> 0.953 | Improved |
Closest papers by meaning
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (TPAMI 2021 · similarity 0.89)
- Salient Objects in Clutter (TPAMI 2022 · similarity 0.89)
- Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (ECCV 2018 · similarity 0.89)
- Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach (TPAMI 2025 · similarity 0.89)
- Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes (ICCV 2025 · similarity 0.89)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · 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.
