Layout Annotation Models
BoundaryNet
Introduced by Trivedi et al. in BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout AnnotationBoundaryNet is a resizing-free approach for layout annotation. The variable-sized user selected region of interest is first processed by an attention-guided skip network. The network optimization is guided via Fast Marching distance maps to obtain a good quality initial boundary estimate and an associated feature representation. These outputs are processed by a Residual Graph Convolution Network optimized using Hausdorff loss to obtain the final region boundary.
Source: BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
