PASCAL Boundaries: A Class-Agnostic Semantic Boundary Dataset
This provides a large-scale dataset for class-agnostic semantic boundary detection, enabling research in computer vision, though it is incremental in expanding existing edge detection resources.
The authors tackled the ambiguity in edge detection by creating the PASCAL Boundaries dataset, which includes over 10k images with ground truth boundaries across 459 semantic classes, and proposed a novel multi-scale deep network for boundary detection.
In this paper, we address the boundary detection task motivated by the ambiguities in current definition of edge detection. To this end, we generate a large database consisting of more than 10k images (which is 20x bigger than existing edge detection databases) along with ground truth boundaries between 459 semantic classes including both foreground objects and different types of background, and call it the PASCAL Boundaries dataset, which will be released to the community. In addition, we propose a novel deep network-based multi-scale semantic boundary detector and name it Multi-scale Deep Semantic Boundary Detector (M-DSBD). We provide baselines using models that were trained on edge detection and show that they transfer reasonably to the task of boundary detection. Finally, we point to various important research problems that this dataset can be used for.