PottsMGNet: A Mathematical Explanation of Encoder-Decoder Based Neural Networks

• URL: http://arxiv.org/abs/2307.09039v2
• Date: Fri, 15 Sep 2023 13:53:44 GMT
• Title: PottsMGNet: A Mathematical Explanation of Encoder-Decoder Based Neural Networks
• Authors: Xue-Cheng Tai, Hao Liu, Raymond Chan
• Abstract summary: 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.
• Score: 7.668812831777923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For problems in image processing and many other fields, a large class of effective neural networks has encoder-decoder-based architectures. Although these networks have made impressive performances, mathematical explanations of their architectures are still underdeveloped. In this paper, we study the encoder-decoder-based network architecture from the algorithmic perspective and provide a mathematical explanation. We use the two-phase Potts model for image segmentation as an example for our explanations. We associate the segmentation problem with a control problem in the continuous setting. Then, multigrid method and operator splitting scheme, the PottsMGNet, are used to discretize the continuous control model. We show that the resulting discrete PottsMGNet is equivalent to an encoder-decoder-based network. With minor modifications, it is shown that a number of the popular encoder-decoder-based neural networks are just instances of the proposed PottsMGNet. By incorporating the Soft-Threshold-Dynamics into the PottsMGNet as a regularizer, the PottsMGNet has shown to be robust with the network parameters such as network width and depth and achieved remarkable performance on datasets with very large noise. In nearly all our experiments, the new network always performs better or as good on accuracy and dice score than existing networks for image segmentation.

Related papers

• Connections between Operator-splitting Methods and Deep Neural Networks with Applications in Image Segmentation [7.668812831777923]
  How to make connections between deep neural networks and mathematical algorithms is still under development. We show an algorithmic explanation for deep neural networks, especially in their connections with operator splitting. We propose two networks inspired by operator-splitting methods solving the Potts model.
  arXiv  Detail & Related papers  (2023-07-18T08:06:14Z)
• Continuous U-Net: Faster, Greater and Noiseless [2.6163085620813287]
  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.
  arXiv  Detail & Related papers  (2023-02-01T17:46:00Z)
• ViGU: Vision GNN U-Net for Fast MRI [1.523157765626545]
  We introduce a novel Vision GNN type network for fast MRI called Vision GNN U-Net (ViGU) A U-shape network is developed using several graph blocks in symmetrical encoder and decoder paths. We demonstrate, through numerical and visual experiments, that the proposed ViGU and GAN variant outperform existing CNN and GAN-based methods.
  arXiv  Detail & Related papers  (2023-01-23T12:51:57Z)
• 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)
• Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation [98.05643473345474]
  We propose a novel decoder, termed dynamic neural representational decoder (NRD) As each location on the encoder's output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient.
  arXiv  Detail & Related papers  (2021-07-30T04:50:56Z)
• Analysis of Convolutional Decoder for Image Caption Generation [1.2183405753834562]
  Convolutional Neural Networks have been proposed for Sequence Modelling tasks such as Image Caption Generation. Unlike Recurrent Neural Network based Decoder, Convolutional Decoder for Image Captioning does not generally benefit from increase in network depth. We observe that Convolutional Decoders show performance comparable with Recurrent Decoders only when trained using sentences of smaller length which contain up to 15 words.
  arXiv  Detail & Related papers  (2021-03-08T17:25:31Z)
• 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)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Attentive Graph Neural Networks for Few-Shot Learning [74.01069516079379]
  Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize the model from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep. We propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism.
  arXiv  Detail & Related papers  (2020-07-14T07:43:09Z)
• DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation [2.3574651879602215]
  Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) We propose an efficient network architecture by considering advantages of both networks.
  arXiv  Detail & Related papers  (2020-04-28T12:16:24Z)
• 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.