Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation

06/23/2020
by   Ali Hatamizadeh, et al.
38

Image segmentation is a fundamental and challenging problem in computer vision with applications spanning multiple areas, such as medical imaging, remote sensing, and autonomous vehicles. Recently, convolutional neural networks (CNNs) have gained traction in the design of automated segmentation pipelines. Although CNN-based models are adept at learning abstract features from raw image data, their performance is dependent on the availability and size of suitable training datasets. Additionally, these models are often unable to capture the details of object boundaries and generalize poorly to unseen classes. In this thesis, we devise novel methodologies that address these issues and establish robust representation learning frameworks for fully-automatic semantic segmentation in medical imaging and mainstream computer vision. In particular, our contributions include (1) state-of-the-art 2D and 3D image segmentation networks for computer vision and medical image analysis, (2) an end-to-end trainable image segmentation framework that unifies CNNs and active contour models with learnable parameters for fast and robust object delineation, (3) a novel approach for disentangling edge and texture processing in segmentation networks, and (4) a novel few-shot learning model in both supervised settings and semi-supervised settings where synergies between latent and image spaces are leveraged to learn to segment images given limited training data.

READ FULL TEXT

page 21

page 22

page 24

page 25

page 26

page 32

research
07/22/2020

End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagery

The automated segmentation of buildings in remote sensing imagery is a c...
research
01/11/2017

CNN-based Segmentation of Medical Imaging Data

Convolutional neural networks have been applied to a wide variety of com...
research
02/11/2020

Edge-Gated CNNs for Volumetric Semantic Segmentation of Medical Images

Textures and edges contribute different information to image recognition...
research
06/26/2019

Topology Maintained Structure Encoding

Deep learning has been used as a powerful tool for various tasks in comp...
research
02/10/2021

A View of Regularized Approaches for Image Segmentation

Image segmentation is a central topic in image processing and computer v...
research
10/25/2021

Interactive Segmentation via Deep Learning and B-Spline Explicit Active Surfaces

Automatic medical image segmentation via convolutional neural networks (...
research
03/16/2017

Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification

Dynamic Textures (DTs) are sequences of images of moving scenes that exh...

Please sign up or login with your details

Forgot password? Click here to reset