Research map / Detection and segmentation / CNN features
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
Hongmei Song, Wenguan Wang, Sanyuan Zhao, Jianbing Shen, Kin-Man Lam
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 static-image training data (ablation) | PDB-ConvLSTM model · DAVIS | maximum F-measure: 0.753 -> 0.849 | Improved |
| add static-image training data (ablation) | PDB-ConvLSTM model · DAVIS | MAE: 0.049 -> 0.030 | Improved |
| replace fully connected LSTM with PDB-ConvLSTM (ablation) | FC-LSTM · DAVIS | maximum F-measure: 0.705 -> 0.849 | Improved |
| replace ConvLSTM with PDB-ConvLSTM (ablation) | ConvLSTM · DAVIS | maximum F-measure: 0.783 -> 0.849 | Improved |
| add bidirectional pathway to ConvLSTM (ablation) | ConvLSTM · DAVIS | maximum F-measure: 0.783 -> 0.786 | Improved |
| add deeper fusion to bidirectional ConvLSTM (ablation) | B-ConvLSTM · DAVIS | maximum F-measure: 0.786 -> 0.809 | Improved |
| add parallel pyramid dilated ConvLSTMs to DB-ConvLSTM (ablation) | DB-ConvLSTM · DAVIS | maximum F-measure: 0.809 -> 0.849 | Improved |
| add parallel pyramid dilated ConvLSTMs to DB-ConvLSTM (ablation) | DB-ConvLSTM · FBMS | maximum F-measure: 0.799 -> 0.815 | Improved |
| use PDC module with concatenation instead of ASPP (ablation) | ASPP · DAVIS | maximum F-measure: 0.703 -> 0.849 | Improved |
| use multi-scale dilation rates instead of single rate (ablation) | PDC single rate · DAVIS | maximum F-measure: 0.704 -> 0.849 | Improved |
| apply CRF refinement to saliency maps | Ours · DAVIS unsupervised VOS | J mean: 74.3 -> 77.2 | Improved |
| apply CRF refinement to saliency maps | Ours · FBMS unsupervised VOS | J mean: 72.3 -> 74.0 | Improved |
Closest papers by meaning
- Salient Object Detection with Recurrent Fully Convolutional Networks (TPAMI 2018 · similarity 0.89)
- Salient Object Detection With Pyramid Attention and Salient Edges (CVPR 2019 · similarity 0.89)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.89)
- Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR 2019 · similarity 0.89)
- Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection (ICCV 2017 · similarity 0.88)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (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.
