Research map / Detection and segmentation / CNN features
F³Net: Fusion, Feedback and Focus for Salient Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use F³Net instead of the strongest listed baseline | Salient object detection · ECSSD | MAE: .037 -> .033 | Helped |
| Use F³Net instead of the strongest listed baseline | Salient object detection · PASCAL-S | MAE: .070 -> .062 | Helped |
| Use F³Net instead of the strongest listed baseline | Salient object detection · DUTS-TE | MAE: .040 -> .035 | Helped |
| Use F³Net instead of the strongest listed baseline | Salient object detection · HKU-IS | MAE: .032 -> .028 | Helped |
| Use F³Net instead of the strongest listed baseline | Salient object detection · DUT-OMRON | MAE: .057 -> .053 | Helped |
| Use PPA loss rather than BCE-only training (ablation) | F³Net · DUTS-TE | MAE: .051 -> .043 | Helped |
| Add multi-level supervision (ablation) | F³Net with PPA loss · DUTS-TE | MAE: .043 -> .040 | Helped |
| Add cross feature module (ablation) | F³Net with PPA and MLS · DUTS-TE | MAE: .040 -> .036 | Helped |
| Add cascaded feedback decoder (ablation) | F³Net with PPA, MLS, and CFM · DUTS-TE | MAE: .036 -> .035 | Helped |
| Set PPA γ to 5 rather than 3, 4, or 6 (ablation) | F³Net · DUTS-TE | MAE: .038, .037, .035, .038 | Helped |
| Use two CFD sub-decoders rather than one, three, or four (ablation) | F³Net · DUTS-TE | MAE: .037, .035, .036, .038 | Helped |
Closest papers by meaning
- Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR 2019 · similarity 0.91)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.91)
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.90)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.90)
- A Bi-Directional Message Passing Model for Salient Object Detection (CVPR 2018 · similarity 0.89)
- Exploring Salient Object Detection with Adder Neural Networks (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.