Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss
Significant progress has been made in boundary detection with the help of convolutional neural networks. Recent boundary detection models not only focus on real object boundary detection but also "crisp" boundaries (precisely localized along the object's contour). There are two method...
Saved in:
Published in | IEEE transactions on multimedia Vol. 23; pp. 761 - 771 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Significant progress has been made in boundary detection with the help of convolutional neural networks. Recent boundary detection models not only focus on real object boundary detection but also "crisp" boundaries (precisely localized along the object's contour). There are two methods to evaluate crisp boundary performance. One uses more strict tolerance to measure the distance between the ground truth and the detected contour. The other focuses on evaluating the contour map without any postprocessing. In this study, we analyze both methods and conclude that both methods are two aspects of crisp contour evaluation. Accordingly, we propose a novel network named deep refinement network (DRNet) that stacks multiple refinement modules to achieve richer feature representation and a novel loss function, which combines cross-entropy and dice loss through effective adaptive fusion. Experimental results demonstrated that we achieve state-of-the-art performance for several available datasets. |
---|---|
ISSN: | 1520-9210 1941-0077 |
DOI: | 10.1109/TMM.2020.2987685 |