Research map / Detection and segmentation / CNN features
Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection
Wenhu Zhang, Liangli Zheng, Huanyu Wang, Xintian Wu, Xi Li
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 Saliency Hierarchy Module with static kernels (ablation) | vanilla U-Net ResNet-50 · DUTS-TE | mean F-measure: 82.0% -> 85.4% | Improved |
| add Saliency Hierarchy Module with static kernels (ablation) | vanilla U-Net ResNet-50 · DUT-O | mean F-measure: 73.4% -> 77.2% | Improved |
| add Hyper Kernel Generator (ablation) | B + SHM (Static) · DUT-O | mean F-measure: 77.2% -> 78.4% | Improved |
| use Erode sub-saliency supervision (ablation) | SHNet · DUTS-TE | mean F-measure: 1.9% | Improved |
| use Grad-CAM instead of DT prior guidance (ablation) | SHNet · DUTS-TE | mean F-measure: .850 -> .854 | Improved |
| add Grad-CAM prior guidance (ablation) | SHNet · DUTS-TE | mean F-measure: .830 -> .854 | Improved |
| generate kernels with a transformer instead of conv (Hyper Conv) (ablation) | SHNet HKG · DUTS-TE | mean F-measure: .859 -> .867 | Improved |
| generate hyper-kernels with transformer instead of static kernels (ablation) | SHNet HKG · DUTS-TE | mean F-measure: .854 -> .867 | Improved |
| share hyper-kernels across SHMs instead of multiple transformers (ablation) | SHNet HKG · DUTS-TE | mean F-measure: .866 -> .867 | No clear effect |
| share hyper-kernels across SHMs instead of multiple transformers (ablation) | SHNet HKG · params and GFLOPs | Params (M) and GFLOPs: 61.0 -> 32.4 params; 15.7 -> 15.1 GFLOPs | Improved |
| use number of saliency levels N=3 versus over-decomposition (ablation) | SHNet · DUTS-TE and ECSSD | mean F-measure | Mixed |
| use larger 352 input instead of 256 | SHNet ResNet-50 · DUTS-TE | mean F-measure: .867 -> .883 | Improved |
Closest papers by meaning
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.91)
- DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection (CVPR 2016 · similarity 0.91)
- Salient Object Detection: A Discriminative Regional Feature Integration Approach (IJCV 2016 · similarity 0.91)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · similarity 0.90)
- Towards High-Resolution Salient Object Detection (ICCV 2019 · similarity 0.90)
- ELD-Net: An Efficient Deep Learning Architecture for Accurate Saliency Detection (TPAMI 2017 · 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.
