Segmenting two-dimensional structures with strided tensor networks
- URL: http://arxiv.org/abs/2102.06900v1
- Date: Sat, 13 Feb 2021 11:06:34 GMT
- Title: Segmenting two-dimensional structures with strided tensor networks
- Authors: Raghavendra Selvan, Erik B Dam, Jens Petersen
- Abstract summary: 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.
- Score: 1.952097552284465
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Tensor networks provide an efficient approximation of operations involving
high dimensional tensors and have been extensively used in modelling quantum
many-body systems. More recently, supervised learning has been attempted with
tensor networks, primarily focused on tasks such as image classification. In
this work, we propose a novel formulation of tensor networks for supervised
image segmentation which allows them to operate on high resolution medical
images. We use the matrix product state (MPS) tensor network on non-overlapping
patches of a given input image to predict the segmentation mask by learning a
pixel-wise linear classification rule in a high dimensional space. The proposed
model is end-to-end trainable using backpropagation. It is implemented as a
Strided Tensor Network to reduce the parameter complexity. The performance of
the proposed method is evaluated on two public medical imaging datasets and
compared to relevant baselines. The evaluation shows that the strided tensor
network yields competitive performance compared to CNN-based models while using
fewer resources. Additionally, based on the experiments we discuss the
feasibility of using fully linear models for segmentation tasks.
Related papers
- Deep tensor networks with matrix product operators [0.0]
We introduce deep tensor networks, which are exponentially wide neural networks based on the tensor network representation of the weight matrices.
We evaluate the proposed method on the image classification (MNIST, FashionMNIST) and sequence prediction (cellular automata) tasks.
arXiv Detail & Related papers (2022-09-16T09:09:52Z) - Two-Stream Graph Convolutional Network for Intra-oral Scanner Image
Segmentation [133.02190910009384]
We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes.
Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
arXiv Detail & Related papers (2022-04-19T10:41:09Z) - Weakly-supervised fire segmentation by visualizing intermediate CNN
layers [82.75113406937194]
Fire localization in images and videos is an important step for an autonomous system to combat fire incidents.
We consider weakly supervised segmentation of fire in images, in which only image labels are used to train the network.
We show that in the case of fire segmentation, which is a binary segmentation problem, the mean value of features in a mid-layer of classification CNN can perform better than conventional Class Activation Mapping (CAM) method.
arXiv Detail & Related papers (2021-11-16T11:56:28Z) - Optimising for Interpretability: Convolutional Dynamic Alignment
Networks [108.83345790813445]
We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets)
Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns.
CoDA Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions.
arXiv Detail & Related papers (2021-09-27T12:39:46Z) - Patch-based medical image segmentation using Quantum Tensor Networks [1.5899411215927988]
We formulate image segmentation in a supervised setting with tensor networks.
The key idea is to first lift the pixels in image patches to exponentially high dimensional feature spaces.
The performance of the proposed model is evaluated on three 2D- and one 3D- biomedical imaging datasets.
arXiv Detail & Related papers (2021-09-15T07:54:05Z) - Tensor-Train Networks for Learning Predictive Modeling of
Multidimensional Data [0.0]
A promising strategy is based on tensor networks, which have been very successful in physical and chemical applications.
We show that the weights of a multidimensional regression model can be learned by means of tensor networks with the aim of performing a powerful compact representation.
An algorithm based on alternating least squares has been proposed for approximating the weights in TT-format with a reduction of computational power.
arXiv Detail & Related papers (2021-01-22T16:14:38Z) - Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation.
We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths.
In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
arXiv Detail & Related papers (2020-12-09T12:40:13Z) - 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) - Anomaly Detection with Tensor Networks [2.3895981099137535]
We exploit the memory and computational efficiency of tensor networks to learn a linear transformation over a space with a dimension exponential in the number of original features.
We produce competitive results on image datasets, despite not exploiting the locality of images.
arXiv Detail & Related papers (2020-06-03T20:41:30Z) - Tensor Networks for Medical Image Classification [0.456877715768796]
We focus on the class of Networks, which has been a work horse for physicists in the last two decades to analyse quantum many-body systems.
We extend the Matrix Product State tensor networks to be useful in medical image analysis tasks.
We show that tensor networks are capable of attaining performance that is comparable to state-of-the-art deep learning methods.
arXiv Detail & Related papers (2020-04-21T15:02:58Z) - 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.