Research map / Detection and segmentation / Weakly supervised detection and segmentation
Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing
Check 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 saliency-guided weight assignment and the smoothness prior (ablation) | SGDL · MSRC21 | mAcc: 56 -> 82 | Helped |
| Use saliency-guided weight assignment and the smoothness prior (ablation) | SGDL · MSRC21 | mIOU: 49 -> 70 | Helped |
| Add the smoothness prior (ablation) | SGDL · MSRC21 | mAcc: 77 -> 82 | Helped |
| Add the smoothness prior (ablation) | SGDL · MSRC21 | mIOU: 60 -> 70 | Helped |
| Add saliency guidance while leaving out the smoothness prior (ablation) | SGDL-Sm · MSRC21 | mAcc: 56 -> 77 | Helped |
| Add saliency guidance while leaving out the smoothness prior (ablation) | SGDL-Sm · MSRC21 | mIOU: 49 -> 60 | Helped |
| Use SGDL instead of k-NN SG+HG | weakly supervised image parsing · MSRC21 | mAcc: 80 -> 82 | Helped |
| Use SGDL instead of k-NN SG+HG | weakly supervised image parsing · PASCAL VOC07 | mAcc: 47 -> 54 | Helped |
| Use SGDL instead of STC | weakly supervised image parsing · PASCAL VOC12 val set | mIOU: 50 -> 34 | Hurt |
Closest papers by meaning
- Railroad Is Not a Train: Saliency As Pseudo-Pixel Supervision for Weakly Supervised Semantic Segmentation (CVPR 2021 · similarity 0.87)
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (AAAI 2021 · similarity 0.87)
- Multi-Source Weak Supervision for Saliency Detection (CVPR 2019 · similarity 0.86)
- Exploiting Saliency for Object Segmentation From Image Level Labels (CVPR 2017 · similarity 0.86)
- Learning Saliency-Free Model with Generic Features for Weakly-Supervised Semantic Segmentation (AAAI 2020 · similarity 0.86)
- Learning to Detect Salient Objects With Image-Level Supervision (CVPR 2017 · similarity 0.86)
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.