Research map / Detection and segmentation / CNN features
EGNet: Edge Guidance Network for Salient Object Detection
Jia-Xing Zhao, Jiang-Jiang Liu, Deng-Ping Fan, Yang Cao, Jufeng Yang, Ming-Ming Cheng
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 salient edge features via side path (edge_PROG) (ablation) | U-Net baseline · SOD | MaxF: .851 -> .873 | Improved |
| add salient edge features via side path (edge_PROG) (ablation) | U-Net baseline · DUTS-TE | MaxF: .855 -> .872 | Improved |
| use top-down location propagation for edge features (edge_TDLP) instead of side path (ablation) | edge_PROG · SOD | MaxF: .873 -> .882 | Improved |
| use top-down location propagation for edge features (edge_TDLP) instead of side path (ablation) | edge_PROG · DUTS-TE | MaxF: .872 -> .879 | Improved |
| add complementary edge and location modeling (edge_TDLP) (ablation) | U-Net baseline · SOD / DUTS-TE | MaxF: 3.1%, 2.4% | Improved |
| add NLDF-style IoU edge loss (edge_NLDF) (ablation) | U-Net baseline · DUTS-TE | MaxF: .855 -> .866 | No clear effect |
| add NLDF-style IoU edge loss (edge_NLDF) (ablation) | U-Net baseline · SOD | MaxF: .851 -> .857 | No clear effect |
| use one-to-one guidance fusion instead of progressive fusion (ablation) | edge_TDLP model · SOD | MaxF: .882 -> .890 | Improved |
| use one-to-one guidance fusion instead of progressive fusion (ablation) | edge_TDLP model · DUTS-TE | MaxF: .880 -> .893 | Improved |
| progressive multi-resolution fusion (MRF_PROG) on top of edge_TDLP (ablation) | edge_TDLP model · SOD | MAE: .100 -> .106 | Hurt |
| use EGNet salient edges instead of NLDF edges | salient edge detection · DUTS | MaxF: 0.429 -> 0.539 | Improved |
| use EGNet instead of PiCANet (ResNet backbone) | salient object detection · SOD | MaxF: 0.861 -> 0.890 | Improved |
Later papers that compared with this method
14 later accepted papers report EGNet as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- Large-Field Contextual Feature Learning for Glass Detection (TPAMI 2022 · better on 2 of 2 shared results)
- Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (ICCV 2021 · better on 6 of 6 shared results)
- Scene Context-Aware Salient Object Detection (ICCV 2021 · better on 3 of 3 shared results)
- Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting (ICCV 2021 · better on 3 of 3 shared results)
- Multi-scale Graph Fusion for Co-saliency Detection (AAAI 2021 · better on 1 of 2 shared results)
- Locate Globally, Segment Locally: A Progressive Architecture With Knowledge Review Network for Salient Object Detection (AAAI 2021 · better on 1 of 1 shared result)
- Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection (CVPR 2021 · better on 0 of 1 shared result)
- Camouflaged Object Detection (CVPR 2020 · better on 9 of 9 shared results)
6 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PiCANet — PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (CVPR 2018) · better on 7 of 7 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
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.88)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.87)
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.87)
- Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (ICCV 2019 · similarity 0.87)
- Accurate RGB-D Salient Object Detection via Collaborative Learning (ECCV 2020 · similarity 0.87)
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.
