Research map / Detection and segmentation / CNN features
Global Context-Aware Progressive Aggregation Network 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 GCPANet instead of the strongest reported baseline | Salient object detection · ECSSD | MAE: 0.037 -> 0.035 | Helped |
| Add FIA to the baseline (ablation) | GCPANet baseline · ECSSD | MAE: 0.0456 -> 0.0390 | Helped |
| Add SR to the FIA model (ablation) | GCPANet baseline with FIA · ECSSD | MAE: 0.0390 -> 0.0365 | Helped |
| Add HA to the FIA and SR model (ablation) | GCPANet baseline with FIA and SR · ECSSD | MAE: 0.0365 -> 0.0364 | Helped |
| Add GCF to the FIA, SR, and HA model (ablation) | GCPANet · ECSSD | MAE: 0.0364 -> 0.0348 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · ECSSD | MAE: 0.0361 -> 0.0348 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · HKU-IS | MAE: 0.0313 -> 0.0309 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · PASCAL-S | MAE: 0.0628 -> 0.0614 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · DUT-OMRON | MAE: 0.0590 -> 0.0563 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · DUTS-TE | MAE: 0.0388 -> 0.0380 | Helped |
| Use stage-specific GCF instead of sharing global context features across stages (ablation) | GCPANet · SOD | MAE: 0.0915 -> 0.0874 | Helped |
Closest papers by meaning
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.91)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.89)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.89)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- A Simple Pooling-Based Design for Real-Time Salient Object Detection (CVPR 2019 · similarity 0.88)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · similarity 0.86)
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.