Context Attention Network for Skeleton Extraction

05/24/2022
by   Zixuan Huang, et al.
6

Skeleton extraction is a task focused on providing a simple representation of an object by extracting the skeleton from the given binary or RGB image. In recent years many attractive works in skeleton extraction have been made. But as far as we know, there is little research on how to utilize the context information in the binary shape of objects. In this paper, we propose an attention-based model called Context Attention Network (CANet), which integrates the context extraction module in a UNet architecture and can effectively improve the ability of network to extract the skeleton pixels. Meanwhile, we also use some novel techniques including distance transform, weight focal loss to achieve good results on the given dataset. Finally, without model ensemble and with only 80 achieves 0.822 F1 score during the development phase and 0.8507 F1 score during the final phase of the Pixel SkelNetOn Competition, ranking 1st place on the leaderboard.

READ FULL TEXT

page 1

page 3

page 5

research
07/02/2019

SkeletonNet: Shape Pixel to Skeleton Pixel

Deep Learning for Geometric Shape Understating has organized a challenge...
research
06/01/2019

Parametric Shape Modeling and Skeleton Extraction with Radial Basis Functions using Similarity Domains Network

We demonstrate the use of similarity domains (SDs) for shape modeling an...
research
12/22/2021

Binary Image Skeletonization Using 2-Stage U-Net

Object Skeletonization is the process of extracting skeletal, line-like ...
research
09/13/2016

DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images

Object skeletons are useful for object representation and object detecti...
research
03/31/2016

Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs

Object skeleton is a useful cue for object detection, complementary to t...
research
10/07/2019

Skeleton based simulation of turbidite channels system

A new approach to model turbidite channels using training images is pres...
research
01/28/2022

DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation

Accurate segmentation of the vertebra is an important prerequisite in va...

Please sign up or login with your details

Forgot password? Click here to reset