Research map / Detection and segmentation / CNN features
Employing Deep Part-Object Relationships for Salient Object Detection
Yi Liu, Qiang Zhang, Dingwen Zhang, Jungong Han
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 TSPOANet on top of FLNet (ablation) | FLNet baseline · ECSSD | F-measure: 0.8250 -> 0.8816 | Improved |
| add TSPOANet on top of FLNet (ablation) | FLNet baseline · ECSSD | MAE: 0.0694 -> 0.0521 | Improved |
| use two-stream capsule assignment instead of single stream (ablation) | POANet · ECSSD | F-measure: 0.8706 -> 0.8816 | Improved |
| use two-stream capsule assignment instead of single stream (ablation) | POANet · ECSSD | MAE: 0.0644 -> 0.0521 | Improved |
| use FLNet instead of Conv+ReLU feature extractor (ablation) | SSPOANet · ECSSD | F-measure: 0.6545 -> 0.8706 | Improved |
| use FLNet instead of Conv+ReLU feature extractor (ablation) | SSPOANet · ECSSD | MAE: 0.1504 -> 0.0644 | Improved |
| use 4 or 8 streams instead of 2 (ablation) | TSPOANet · ECSSD | convergence: non-convergence with 4 and 8 streams, works with 2 | Hurt |
| use TSPOANet instead of BMP | TSPOANet · DUTS | F-measure: 0.7505 -> 0.7993 | Improved |
| use TSPOANet instead of BMP | TSPOANet · ECSSD | MAE: 0.0447 -> 0.0515 | Mixed |
Closest papers by meaning
- Part-Object Relational Visual Saliency (TPAMI 2021 · similarity 0.93)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.90)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.90)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.89)
- Delving Into Salient Object Subitizing and Detection (ICCV 2017 · similarity 0.88)
- CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection (CVPR 2019 · 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.
