Back to Search
Start Over
Discretely-constrained deep network for weakly supervised segmentation
- Publication Year :
- 2019
- Publisher :
- arXiv, 2019.
-
Abstract
- An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization priors can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on two benchmark datasets for medical image segmentation show our method to provide significant improvements compared to existing approaches in terms of segmentation accuracy, constraint satisfaction and convergence speed.
- Subjects :
- Continuous optimization
FOS: Computer and information sciences
0209 industrial biotechnology
Computer science
Cognitive Neuroscience
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
02 engineering and technology
Image segmentation
Regularization (mathematics)
Convolutional neural network
Pattern Recognition, Automated
020901 industrial engineering & automation
Artificial Intelligence
Discrete optimization
Computer Science::Computer Vision and Pattern Recognition
0202 electrical engineering, electronic engineering, information engineering
Image Processing, Computer-Assisted
Humans
020201 artificial intelligence & image processing
Segmentation
Neural Networks, Computer
Supervised Machine Learning
Algorithm
Algorithms
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....471135ae62d9c493243805158dcdd166
- Full Text :
- https://doi.org/10.48550/arxiv.1908.05770