Research map / Label-efficient and robust learning / Domain adaptation and generalization
Deepstrip: High-Resolution Boundary Refinement
Peng Zhou, Brian Price, Scott Cohen, Gregg Wilensky, Larry S. Davis
Check 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 |
|---|---|---|---|
| Use strip-based boundary prediction with the full selection and loss framework | DeepStrip · DAVIS 2016 and PixaHR 8×, 16×, 32× | Boundary F score: DAVIS 2016: 0.320 -> 0.423 (F (0 pix)); PixaHR 8×: 0.334 -> 0.416 (F (1 pix)); PixaHR 16×: 0.303 -> 0.396 (F (1 pix)); P | Improved |
| Add Dice loss (ablation) | U-Net strip · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.303 -> 0.323; 0.303 -> 0.320 | Improved |
| Add a selection layer to choose target boundaries (ablation) | U-Net strip with Dice loss · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.323 -> 0.372; 0.320 -> 0.328 | Improved |
| Add boundary distance loss (ablation) | U-Net strip with Dice loss and selection · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.372 -> 0.390; 0.328 -> 0.342 | Improved |
| Add C0 continuity regularization (ablation) | DeepStrip without matching loss · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.390 -> 0.405; 0.342 -> 0.365 | Improved |
| Add matching loss (ablation) | DeepStrip · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.405 -> 0.423; 0.365 -> 0.396 | Improved |
| Adapt strip height for one contour segment (ablation) | DeepStrip · PixaHR 32× | F (1 pix): 0.330 -> 0.353 | Improved |
| Adapt strip height independently for two segments (ablation) | DeepStrip · PixaHR 32× | F (1 pix): 0.353 -> 0.365 | Improved |
| Use image gradient alone for strip reconstruction instead of learned boundary prediction (ablation) | DeepStrip reconstruction · DAVIS 2016 and PixaHR 16× | Boundary F score: 0.423 -> 0.165; 0.396 -> 0.295 | Hurt |
| Vary strip width from factor 1 to 2, with factor 1.5 as the selected trade-off (ablation) | DeepStrip · DAVIS 2016 and PixaHR 16× | Boundary F score: DAVIS 2016: 0.414, 0.416, 0.423; PixaHR 16×: 0.392, 0.415, 0.396 | Mixed |
Closest papers by meaning
- Learning to Predict Crisp Boundaries (ECCV 2018 · similarity 0.87)
- Learning on the Edge: Investigating Boundary Filters in CNNs (IJCV 2019 · similarity 0.86)
- Zero Pixel Directional Boundary by Vector Transform (ICLR 2022 · similarity 0.85)
- Field of Junctions: Extracting Boundary Structure at Low SNR (ICCV 2021 · similarity 0.85)
- Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer (AAAI 2025 · similarity 0.83)
- Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries (CVPR 2025 · similarity 0.83)
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.
