Research map / Detection and segmentation / Weakly supervised detection and segmentation
Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector
Dingwen Zhang, Junwei Han, Yu Zhang
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 superpixel-level fusion map supervision (SFM) (ablation) | OURS · ECSSD | AP: .852 -> .889 | Improved |
| add superpixel-level fusion map supervision (SFM) (ablation) | OURS · DUT-O | AP: .640 -> .715 | Improved |
| add image-level fusion map supervision (IFM) (ablation) | OURS · ECSSD | AP: .844 -> .889 | Improved |
| add image-level fusion map supervision (IFM) (ablation) | OURS · DUT-O | AP: .649 -> .715 | Improved |
| add superpixel-level confidence map (b) (ablation) | OURS · ECSSD | AP: .864 -> .889 | Improved |
| add superpixel-level confidence map (b) (ablation) | OURS · PASCAL-S | AP: .759 -> .791 | Improved |
| add image-level confidence weight (beta) (ablation) | OURS · ECSSD | AP: .876 -> .889 | Improved |
| add image-level confidence weight (beta) (ablation) | OURS · DUT-O | AP: .677 -> .715 | Improved |
| add image-level confidence weight (beta) (ablation) | OURS · SOD | AP: .754 -> .789 | Improved |
| add all four supervisory signals; average drop when removing each (ablation) | OURS · all four datasets | average drop over metrics: SFM (0.4839) > IFM (0.431) > b (0.312) > β (0.186) | Improved |
| use fused unsupervised supervision instead of the best single unsupervised detector | DHSNet-style detector · all four datasets | AP: more than 10% in terms of the AP score | Improved |
| train with human annotation (DHS) instead of fusion pseudo labels | OURS · ECSSD | AP: .889 -> .916 | Improved |
Closest papers by meaning
- Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation (TPAMI 2019 · similarity 0.91)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.90)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.90)
- Learning to Detect Salient Objects With Image-Level Supervision (CVPR 2017 · similarity 0.89)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.89)
- DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision (NeurIPS 2019 · 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.
