Research map / Detection and segmentation / CNN features
Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection
Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, Xiang Ruan
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 the highest-resolution integrated features (Amulet-1/16 to full Amulet) (ablation) | Amulet · DUTS-TE | F-measure: 0.6891 -> 0.7365 | Improved |
| add the highest-resolution integrated features (Amulet-1/16 to full Amulet) (ablation) | Amulet · DUTS-TE | MAE: 0.09110 -> 0.08517 | Improved |
| add the highest-resolution integrated features (Amulet-1/16 to full Amulet) (ablation) | Amulet · ECSSD | F-measure: 0.8523 -> 0.8684 | Improved |
| add the highest-resolution integrated features (Amulet-1/16 to full Amulet) (ablation) | Amulet · ECSSD | MAE: 0.06477 -> 0.05874 | Improved |
| add boundary preserved refinement (BPR) (ablation) | Amulet · ECSSD | MAE: 0.06572 -> 0.05874 | Improved |
| add boundary preserved refinement (BPR) (ablation) | Amulet · DUTS-TE | MAE: 0.09761 -> 0.08517 | Improved |
| add boundary preserved refinement (BPR) (ablation) | Amulet · ECSSD | F-measure: 0.8647 -> 0.8684 | Improved |
| add boundary preserved refinement (BPR) (ablation) | Amulet · DUTS-TE | F-measure: 0.6912 -> 0.7365 | Improved |
| use Amulet-1/16 multi-level aggregation instead of HED aggregation | Amulet-1/16 without BPR · ECSSD | F-measure: 0.8321 -> 0.8521 | Improved |
| use Amulet-1/16 multi-level aggregation instead of FCN-8s aggregation | Amulet-1/16 without BPR · ECSSD | MAE: 0.1343 -> 0.0662 | Improved |
| use Amulet instead of DHS | Amulet · PASCAL-S | F-measure: 0.7741 -> 0.7632 | Hurt |
| use Amulet instead of DCL | Amulet · DUT-OMRON | F-measure: 0.6842 -> 0.6471 | Hurt |
Later papers that compared with this method
11 later accepted papers report Amulet as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- Highly Efficient Salient Object Detection with 100K Parameters (ECCV 2020 · better on 1 of 1 shared result)
- Optimizing the F-Measure for Threshold-Free Salient Object Detection (ICCV 2019 · better on 5 of 5 shared results)
- Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection (ICCV 2019 · better on 1 of 2 shared results)
- Towards High-Resolution Salient Object Detection (ICCV 2019 · better on 2 of 2 shared results)
- Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (ICCV 2019 · better on 2 of 2 shared results)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · better on 3 of 4 shared results)
- PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (CVPR 2018 · better on 3 of 3 shared results)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · better on 2 of 3 shared results)
3 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
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)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.90)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.90)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.90)
- Salient Object Detection: A Discriminative Regional Feature Integration Approach (IJCV 2016 · 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.
