Research map / Detection and segmentation / Open-set and few-shot detection
Learning to Promote Saliency Detectors
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 |
|---|---|---|---|
| Apply the proposed promotion method to SRM | SRM · ECSSD | Fβ: 0.8921 -> 0.9151 | Helped |
| Apply the proposed promotion method to SRM | SRM · HKU-IS | Fβ: 0.8739 -> 0.9042 | Helped |
| Apply the proposed promotion method to SRM | SRM · PASCAL-S | Fβ: 0.8007 -> 0.8240 | Helped |
| Apply the proposed promotion method to SRM | SRM · DUTS-Test | Fβ: 0.7570 -> 0.8023 | Helped |
| Apply the proposed promotion method to SRM | SRM · SOD | Fβ: 0.8004 -> 0.8036 | Helped |
| Apply the proposed promotion method to SRM | SRM · ECSSD | MAE: 0.0542 -> 0.0465 | Helped |
| Apply the proposed promotion method to SRM | SRM · HKU-IS | MAE: 0.0458 -> 0.0388 | Helped |
| Apply the proposed promotion method to SRM | SRM · PASCAL-S | MAE: 0.0850 -> 0.0810 | Helped |
| Apply the proposed promotion method to SRM | SRM · DUTS-Test | MAE: 0.0587 -> 0.0558 | Helped |
| Apply the proposed promotion method to SRM | SRM · SOD | MAE: 0.1265 -> 0.1170 | Helped |
| Use FC-based instead of Conv-based region embedding (ablation) | Promoted UCF, RFCN, and ELD on ECSSD · ECSSD | Fβ: UCF: 0.8805 -> 0.8941; RFCN: 0.8337 -> 0.8885; ELD: 0.8098 -> 0.8820 | Helped |
| Use FC-based instead of Conv-based region embedding (ablation) | Promoted UCF, RFCN, and ELD on ECSSD · ECSSD | MAE: UCF: 0.0560 -> 0.0628; RFCN: 0.1069 -> 0.0570; ELD: 0.0789 -> 0.0592 | Mixed |
Closest papers by meaning
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.90)
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.89)
- Shallow and Deep Convolutional Networks for Saliency Prediction (CVPR 2016 · similarity 0.88)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.88)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.88)
- Deep Saliency With Encoded Low Level Distance Map and High Level Features (CVPR 2016 · 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.