Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss

02/02/2021
by   Yi-Jun Cao, et al.
0

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.

READ FULL TEXT

page 7

page 9

research
09/25/2022

Contour Dice loss for structures with Fuzzy and Complex Boundaries in Fetal MRI

Volumetric measurements of fetal structures in MRI are time consuming an...
research
01/02/2019

Photo-Sketching: Inferring Contour Drawings from Images

Edges, boundaries and contours are important subjects of study in both c...
research
08/06/2019

Contour Loss: Boundary-Aware Learning for Salient Object Segmentation

We present a learning model that makes full use of boundary information ...
research
03/24/2022

SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation

Excellent performance has been achieved on instance segmentation but the...
research
07/12/2023

RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation

Glass-like objects are widespread in daily life but remain intractable t...
research
05/19/2018

Contour location via entropy reduction leveraging multiple information sources

We introduce an algorithm to locate contours of functions that are expen...
research
08/09/2016

Convolutional Oriented Boundaries

We present Convolutional Oriented Boundaries (COB), which produces multi...

Please sign up or login with your details

Forgot password? Click here to reset