Research map / Detection and segmentation / Weakly supervised detection and segmentation
Weakly Supervised Salient Object Detection Using Image Labels
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 |
|---|---|---|---|
| Use alternate saliency-map optimization initialized from MB+ | MB+ · DUT-OMRON | maxF: 0.621 -> 0.722 | Helped |
| Use alternate saliency-map optimization initialized from BSCA | BSCA · DUT-OMRON | maxF: 0.617 -> 0.685 | Helped |
| Use alternate saliency-map optimization initialized from MST | MST · DUT-OMRON | maxF: 0.588 -> 0.691 | Helped |
| Add dense CRF after ASMO (ablation) | ASMO · DUT-OMRON | maxF: 0.722 -> 0.732 | Helped |
| Add dense CRF to the initial MB+ map (ablation) | MB+ · DUT-OMRON | maxF: 0.588 -> 0.630 | Helped |
| Train Multi-FCN on generated saliency maps without CRF or CAM guidance (ablation) | MB+ · DUT-OMRON | maxF: 0.588 -> 0.651 | Helped |
| Add CRF guidance to Multi-FCN training (ablation) | Multi-FCN without CRF or CAM guidance · DUT-OMRON | maxF: 0.651 -> 0.685 | Helped |
| Add CAM-guided annotation updating to CRF-guided Multi-FCN (ablation) | S4 CRF-guided Multi-FCN · DUT-OMRON | maxF: 0.685 -> 0.722 | Helped |
| Apply ASMO with CRF to the training set and add groundtruth masks (ablation) | ASMO+ · HKU-IS | maxF: 0.855 -> 0.913 | Helped |
| Apply ASMO with CRF to the training set and add groundtruth masks (ablation) | ASMO+ · ECSSD | maxF: 0.845 -> 0.918 | Helped |
| Apply ASMO with CRF to the training set and add groundtruth masks (ablation) | ASMO+ · PASCAL-S | maxF: 0.758 -> 0.847 | Helped |
Closest papers by meaning
- Weakly-Supervised Salient Object Detection Using Point Supervision (AAAI 2022 · similarity 0.93)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.93)
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (AAAI 2021 · similarity 0.92)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.92)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.91)
- Learning to Detect Salient Objects With Image-Level Supervision (CVPR 2017 · similarity 0.91)
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.