Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
This work addresses the need for efficient and accurate boundary detection for computer vision tasks, benefiting researchers and practitioners in image segmentation and high-level applications, though it is incremental as it builds on existing CNN methods.
The paper tackles the problem of contour detection and hierarchical segmentation by introducing Convolutional Oriented Boundaries (COB), which uses a single CNN forward pass to produce multiscale oriented contours, resulting in state-of-the-art performance across multiple datasets like BSDS and PASCAL with significant improvements in accuracy.
We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments for low-level applications on BSDS, PASCAL Context, PASCAL Segmentation, and NYUD to evaluate boundary detection performance, showing that COB provides state-of-the-art contours and region hierarchies in all datasets. We also evaluate COB on high-level tasks when coupled with multiple pipelines for object proposals, semantic contours, semantic segmentation, and object detection on MS-COCO, SBD, and PASCAL; showing that COB also improves the results for all tasks.