Research map / Detection and segmentation / CNN features
Towards High-Resolution Salient Object Detection
Yi Zeng, Pingping Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu
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 LRN with attended patch sampling to GSN (ablation) | GSN · HRSOD-Test | F-beta: 0.842 -> 0.877 | Improved |
| add LRN with attended patch sampling to GSN (ablation) | GSN · HRSOD-Test | MAE: 0.047 -> 0.036 | Improved |
| use attended patch sampling instead of random patch sampling (ablation) | GSN+LRN · HRSOD-Test | F-beta: 0.860 -> 0.877 | Improved |
| use attended patch sampling instead of random patch sampling (ablation) | GSN+LRN · HRSOD-Test | S-measure: 0.871 -> 0.883 | Improved |
| add GLFN fusion on top of GSN+APS+LRN (ablation) | GSN+APS+LRN · HRSOD-Test | F-beta: 0.877 -> 0.888 | Improved |
| add GLFN fusion on top of GSN+APS+LRN (ablation) | GSN+APS+LRN · HRSOD-Test | MAE: 0.036 -> 0.030 | Improved |
| use GLFN instead of CRF post-processing (ablation) | GSN+APS+LRN · HRSOD-Test | S-measure: 0.875 -> 0.897 | Improved |
| add CRF post-processing to GSN (ablation) | GSN · HRSOD-Test | S-measure: 0.866 -> 0.852 | Hurt |
| add CRF post-processing to GSN (ablation) | GSN · HRSOD-Test | MAE: 0.047 -> 0.038 | Improved |
| train on DUTS plus HRSOD instead of DUTS only | Ours · DUTS-Test | F-beta: 0.796 -> 0.791 | Hurt |
| train on DUTS plus HRSOD instead of DUTS only | Ours · HRSOD-Test | F-beta: 0.857 -> 0.888 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- RFCN — R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016) · better on 3 of 3 shared results
- Amulet — Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection (ICCV 2017) · 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
- Disentangled High Quality Salient Object Detection (ICCV 2021 · similarity 0.94)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.91)
- ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection (ICML 2024 · similarity 0.91)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.91)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.90)
- HSOD-BIT-V2: A Challenging Benchmark for Hyperspectral Salient Object Detection (AAAI 2025 · similarity 0.89)
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.
