Research map / Detection and segmentation / CNN features
Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
Check 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 CPD instead of VGG16-based state-of-the-art models | Salient object detection · ECSSD | maxF: 0.931 -> 0.936 | Helped |
| Use CPD instead of the strongest listed baseline | Salient object detection · DUT-OMRON | maxF: 0.803 -> 0.794 | Hurt |
| Use CPD instead of PiCANet-R | Salient object detection · DUT-OMRON | FPS: 5 -> 66 | Helped |
| Add holistic attention rather than using initial attention (ablation) | CPD · DUTS | avgF: 0.803 -> 0.813 | Helped |
| Add holistic attention rather than using initial attention (ablation) | CPD · DUTS | MAE: 0.045 -> 0.043 | Helped |
| Use Conv2_2 instead of Conv3_3 as the optimization layer (ablation) | CPD · ECSSD | FPS: 66 -> 38 | Hurt |
| Use Conv4_3 instead of Conv3_3 as the optimization layer (ablation) | CPD · ECSSD | maxF: 0.936 -> 0.931 | Hurt |
| Remove the optimization layer and integrate all-level features (ablation) | CPD · ECSSD | maxF: 0.936 -> 0.922 | Hurt |
| Apply the cascaded partial decoder framework to BMPM | BMPM · DUTS | maxF: 0.850 -> 0.870 | Helped |
| Apply the cascaded partial decoder framework to NLDF | NLDF · DUTS | maxF: 0.830 -> 0.842 | Helped |
| Apply the cascaded partial decoder framework to Amulet | Amulet · DUTS | maxF: 0.832 -> 0.845 | Helped |
| Use CPD for portrait segmentation instead of BMPM | Portrait segmentation · Portrait segmentation | Mean IoU: 96.20% -> 96.60% | Helped |
Closest papers by meaning
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.91)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.91)
- F³Net: Fusion, Feedback and Focus for Salient Object Detection (AAAI 2020 · similarity 0.91)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.91)
- Pyramidal Feature Shrinking for Salient Object Detection (AAAI 2021 · similarity 0.91)
- Exploring Salient Object Detection with Adder Neural Networks (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.