Research map / Detection and segmentation / CNN features
Suppress and Balance: A Simple Gated Network for Salient Object Detection
Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, Lei Zhang
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 multilevel gate units to FPN baseline (ablation) | FPN baseline (VGG-16) · DUTS | F-measure: 0.816 -> 0.840 | Improved |
| add multilevel gate units to FPN baseline (ablation) | FPN baseline (VGG-16) · DUTS | MAE: 0.060 -> 0.053 | Improved |
| add Fold-ASPP to gated baseline (ablation) | gated FPN (VGG-16) · DUTS | F-measure: 0.840 -> 0.866 | Improved |
| add Fold-ASPP to gated baseline (ablation) | gated FPN (VGG-16) · DUTS | MAE: 0.053 -> 0.047 | Improved |
| add parallel branch (ablation) | gated FPN with Fold-ASPP · DUTS | F-measure: 0.866 -> 0.870 | Improved |
| add parallel branch (ablation) | gated FPN with Fold-ASPP · DUTS | MAE: 0.047 -> 0.045 | Improved |
| fold the atrous convolution at rate 6 (ablation) | Atrous(6) · DUTS | F-measure: 0.848 -> 0.860 | Improved |
| fold the atrous convolution at rate 2 (ablation) | Atrous(2) · DUTS | F-measure: 0.840 -> 0.853 | Improved |
| replace ASPP with Fold-ASPP (ablation) | ASPP · DUTS | F-measure: 0.856 -> 0.866 | Improved |
| replace ASPP with Fold-ASPP (ablation) | ASPP · DUTS | MAE: 0.051 -> 0.047 | Improved |
| single Fold(6) layer versus ASPP of three atrous layers (ablation) | Fold(6) · DUTS | F-measure: 0.856 -> 0.860 | Improved |
| use ResNet-50 instead of VGG-16 backbone (ablation) | GateNet · DUTS-test | F-measure: 0.870 -> 0.888 | Improved |
Closest papers by meaning
- Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR 2019 · similarity 0.91)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.91)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.90)
- A Simple Pooling-Based Design for Real-Time Salient Object Detection (CVPR 2019 · similarity 0.90)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.90)
- Pyramidal Feature Shrinking for Salient Object Detection (AAAI 2021 · 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.
