Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation

• URL: http://arxiv.org/abs/2002.03989v1
• Date: Mon, 10 Feb 2020 18:03:44 GMT
• Title: Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation
• Authors: Jun Liu, Xiangyue Wang, Xue-cheng Tai
• Abstract summary: The classification functions in the existing network architecture of CNNs are simple and lack capabilities to handle important spatial information. We propose a novel Soft Threshold Dynamics (STD) framework which can easily integrate many spatial priors into the DCNNs. The proposed method is a general mathematical framework and it can be applied to any semantic segmentation DCNNs.
• Score: 6.282154392910916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We use Deep Convolutional Neural Networks (DCNNs) for image segmentation problems. DCNNs can well extract the features from natural images. However, the classification functions in the existing network architecture of CNNs are simple and lack capabilities to handle important spatial information in a way that have been done for many well-known traditional variational models. Prior such as spatial regularity, volume prior and object shapes cannot be well handled by existing DCNNs. We propose a novel Soft Threshold Dynamics (STD) framework which can easily integrate many spatial priors of the classical variational models into the DCNNs for image segmentation. The novelty of our method is to interpret the softmax activation function as a dual variable in a variational problem, and thus many spatial priors can be imposed in the dual space. From this viewpoint, we can build a STD based framework which can enable the outputs of DCNNs to have many special priors such as spatial regularity, volume constraints and star-shape priori. The proposed method is a general mathematical framework and it can be applied to any semantic segmentation DCNNs. To show the efficiency and accuracy of our method, we applied it to the popular DeepLabV3+ image segmentation network, and the experiments results show that our method can work efficiently on data-driven image segmentation DCNNs.

Related papers

• Segmenting objects with Bayesian fusion of active contour models and convnet priors [0.729597981661727]
  We propose a novel instance segmentation method geared towards Natural Resource Monitoring (NRM) imagery. We formulate the problem as Bayesian maximum a posteriori inference which, in learning the individual object contours, incorporates shape, location, and position priors. In experiments, we tackle the challenging, real-world problem of segmenting individual dead tree crowns and precise contours.
  arXiv  Detail & Related papers  (2024-10-09T20:36:43Z)
• Recurrent Neural Networks for Still Images [0.0]
  We argue that RNNs can effectively handle still images by interpreting the pixels as a sequence. We introduce a novel RNN design tailored for two-dimensional inputs, such as images, and a custom version of BiDirectional RNN (BiRNN) that is more memory-efficient than traditional implementations.
  arXiv  Detail & Related papers  (2024-09-10T06:07:20Z)
• Spatial Bayesian Neural Networks [8.594478422578348]
  We propose a new class of spatial-process models, which we refer to as spatial Bayesian neural networks (SBNNs) An SBNN is calibrated by matching its finite-dimensional distribution at locations on a fine gridding of space to that of a target process of interest. We show that an SBNN can be used to represent a variety of spatial processes often used in practice, such as Gaussian processes, lognormal processes, and max-stable processes.
  arXiv  Detail & Related papers  (2023-11-16T01:22:22Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Deep network series for large-scale high-dynamic range imaging [2.3759432635713895]
  We propose a new approach for large-scale high-dynamic range computational imaging. Deep Neural Networks (DNNs) trained end-to-end can solve linear inverse imaging problems almost instantaneously. Alternative Plug-and-Play approaches have proven effective to address high-dynamic range challenges, but rely on highly iterative algorithms.
  arXiv  Detail & Related papers  (2022-10-28T11:13:41Z)
• Towards a General Purpose CNN for Long Range Dependencies in $\mathrm{N}$D [49.57261544331683]
  We propose a single CNN architecture equipped with continuous convolutional kernels for tasks on arbitrary resolution, dimensionality and length without structural changes. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$mathrmD$) and visual data (2$mathrmD$) Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.
  arXiv  Detail & Related papers  (2022-06-07T15:48:02Z)
• Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution [80.93870349019332]
  We propose a novel HSISR method that uses Transformer instead of CNN to learn the prior of HSIs. Specifically, we first use the gradient algorithm to solve the HSISR model, and then use an unfolding network to simulate the iterative solution processes.
  arXiv  Detail & Related papers  (2021-11-27T15:38:57Z)
• OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression [59.58879331876508]
  We study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. Our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images.
  arXiv  Detail & Related papers  (2021-07-19T22:14:30Z)
• LevelSet R-CNN: A Deep Variational Method for Instance Segmentation [79.20048372891935]
  Currently, many state of the art models are based on the Mask R-CNN framework. We propose LevelSet R-CNN, which combines the best of both worlds by obtaining powerful feature representations. We demonstrate the effectiveness of our approach on COCO and Cityscapes datasets.
  arXiv  Detail & Related papers  (2020-07-30T17:52:18Z)
• A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding [57.1077544780653]
  We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems. We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions. This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end.
  arXiv  Detail & Related papers  (2020-06-26T08:34:54Z)
• Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation [6.163107242394357]
  We propose a technique which can be easily integrated into the commonly used DCNNs for image segmentation. Our method is based on the dual representation of the sigmoid activation function in DCNNs. We show that our method is efficient and outperforms the classical DCNN segmentation methods.
  arXiv  Detail & Related papers  (2020-05-15T11:36:04Z)

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.