Continuous U-Net: Faster, Greater and Noiseless

• URL: http://arxiv.org/abs/2302.00626v1
• Date: Wed, 1 Feb 2023 17:46:00 GMT
• Title: Continuous U-Net: Faster, Greater and Noiseless
• Authors: Chun-Wun Cheng, Christina Runkel, Lihao Liu, Raymond H Chan, Carola-Bibiane Sch\"onlieb, Angelica I Aviles-Rivero
• Abstract summary: We introduce continuous U-Net, a novel family of networks for image segmentation. We provide theoretical guarantees for our network demonstrating faster convergence, higher robustness and less sensitivity to noise. We demonstrate, through extensive numerical and visual results, that our model outperforms existing U-Net blocks for several medical image segmentation benchmarking datasets.
• Score: 2.6163085620813287
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image segmentation is a fundamental task in image analysis and clinical practice. The current state-of-the-art techniques are based on U-shape type encoder-decoder networks with skip connections, called U-Net. Despite the powerful performance reported by existing U-Net type networks, they suffer from several major limitations. Issues include the hard coding of the receptive field size, compromising the performance and computational cost, as well as the fact that they do not account for inherent noise in the data. They have problems associated with discrete layers, and do not offer any theoretical underpinning. In this work we introduce continuous U-Net, a novel family of networks for image segmentation. Firstly, continuous U-Net is a continuous deep neural network that introduces new dynamic blocks modelled by second order ordinary differential equations. Secondly, we provide theoretical guarantees for our network demonstrating faster convergence, higher robustness and less sensitivity to noise. Thirdly, we derive qualitative measures to tailor-made segmentation tasks. We demonstrate, through extensive numerical and visual results, that our model outperforms existing U-Net blocks for several medical image segmentation benchmarking datasets.

Related papers

• PottsMGNet: A Mathematical Explanation of Encoder-Decoder Based Neural Networks [7.668812831777923]
  We study the encoder-decoder-based network architecture from the algorithmic perspective. We use the two-phase Potts model for image segmentation as an example for our explanations. We show that the resulting discrete PottsMGNet is equivalent to an encoder-decoder-based network.
  arXiv  Detail & Related papers  (2023-07-18T07:48:48Z)
• Image Blind Denoising Using Dual Convolutional Neural Network with Skip Connection [2.9689285167236603]
  We propose a novel dual convolutional blind denoising network with skip connection (DCBDNet) The proposed DCBDNet consists of a noise estimation network and a dual convolutional neural network (CNN)
  arXiv  Detail & Related papers  (2023-04-04T08:21:46Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Temporal Graph Network Embedding with Causal Anonymous Walks Representations [54.05212871508062]
  We propose a novel approach for dynamic network representation learning based on Temporal Graph Network. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
  arXiv  Detail & Related papers  (2021-08-19T15:39:52Z)
• Segmenting two-dimensional structures with strided tensor networks [1.952097552284465]
  We propose a novel formulation of tensor networks for supervised image segmentation. The proposed model is end-to-end trainable using backpropagation. The evaluation shows that the strided tensor network yields competitive performance compared to CNN-based models.
  arXiv  Detail & Related papers  (2021-02-13T11:06:34Z)
• Binary Graph Neural Networks [69.51765073772226]
  Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. In this paper, we present and evaluate different strategies for the binarization of graph neural networks. We show that through careful design of the models, and control of the training process, binary graph neural networks can be trained at only a moderate cost in accuracy on challenging benchmarks.
  arXiv  Detail & Related papers  (2020-12-31T18:48:58Z)
• Pairwise Relation Learning for Semi-supervised Gland Segmentation [90.45303394358493]
  We propose a pairwise relation-based semi-supervised (PRS2) model for gland segmentation on histology images. This model consists of a segmentation network (S-Net) and a pairwise relation network (PR-Net) We evaluate our model against five recent methods on the GlaS dataset and three recent methods on the CRAG dataset.
  arXiv  Detail & Related papers  (2020-08-06T15:02:38Z)
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture [82.64881585566825]
  We present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. Our method significantly outperforms the vanilla U-Net as well as other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-01T05:07:49Z)
• DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation [1.6416058750198184]
  DoubleU-Net is a combination of two U-Net architectures stacked on top of each other. We have evaluated DoubleU-Net using four medical segmentation datasets.
  arXiv  Detail & Related papers  (2020-06-08T18:38:24Z)
• CRNet: Cross-Reference Networks for Few-Shot Segmentation [59.85183776573642]
  Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images. With a cross-reference mechanism, our network can better find the co-occurrent objects in the two images. Experiments on the PASCAL VOC 2012 dataset show that our network achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-24T04:55:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.