Research map / Detection and segmentation / Open-set and few-shot detection
Interactive Image Segmentation via Backpropagating Refinement Scheme
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 BRS refinement with the DenseNet segmentation model | Interactive image segmentation · GrabCut, Berkeley, DAVIS, and SBD | NoC 90%: GrabCut 4.79 -> 3.60; Berkeley 5.95 -> 5.08; DAVIS 9.57 -> 8.24; SBD 10.78 -> 9.78 | Helped |
| Use BRS-DenseNet instead of LD | Interactive image segmentation · DAVIS and SBD | AuC IoU: DAVIS 0.871 -> 0.867; SBD 0.852 -> 0.842 | Hurt |
| Use BRS-DenseNet instead of LD | Interactive image segmentation · GrabCut and Berkeley | AuC IoU: GrabCut 0.911 -> 0.919; Berkeley 0.902 -> 0.912 | Helped |
| Add BRS to the fine-decoder model (ablation) | Interactive image segmentation · GrabCut and Berkeley | NoC 90%: GrabCut 6.12 -> 3.60; Berkeley 7.65 -> 5.08 | Helped |
| Add the fine decoder (ablation) | Interactive image segmentation · GrabCut and Berkeley | NoC 90%: GrabCut 17.4 -> 3.60; Berkeley 19.63 -> 5.08 | Helped |
| Add BRS to the model without a fine decoder (ablation) | Interactive image segmentation · GrabCut and Berkeley | NoC 90%: GrabCut 17.4 -> 10.28; Berkeley 19.63 -> 15.30 | Helped |
| Add one user annotation with BRS | FCN · PASCAL VOC 2012 validation | average accuracy (%): 65.4 -> 70.9 | Helped |
| Add five user annotations with BRS | FCN · PASCAL VOC 2012 validation | average accuracy (%): 65.4 -> 74.4 | Helped |
| Add five user annotations with BRS | U-Net · PhC-U373 test sequences | average IoU (%): 88.2 -> 89.6 | Helped |
Closest papers by meaning
- Variance-Insensitive and Target-Preserving Mask Refinement for Interactive Image Segmentation (AAAI 2024 · similarity 0.86)
- MFP: Making Full Use of Probability Maps for Interactive Image Segmentation (CVPR 2024 · similarity 0.85)
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 2024 · similarity 0.85)
- Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts (CVPR 2024 · similarity 0.85)
- CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation (AAAI 2024 · similarity 0.84)
- FocSAM: Delving Deeply into Focused Objects in Segmenting Anything (CVPR 2024 · similarity 0.84)
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.