Open AccessPosted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
Reads0
Chats0
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.Abstract:
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at this http URL .read more
Citations
More filters
Proceedings ArticleDOI
Deep Learning with Skip Connection Attention for Choroid Layer Segmentation in OCT Images
Xiaoqian Mao,Yitian Zhao,Bang Chen,Yuhui Ma,Zaiwang Gu,Shenshen Gu,Jianlong Yang,Jun Cheng,Jiang Liu +8 more
TL;DR: A novel Skip Connection Attention (SCA) module which is integrated into the U-Shape architecture is proposed to improve the precision of choroid layer segmentation in Optical Coherence Tomography (OCT) images.
Journal ArticleDOI
Point cloud semantic scene segmentation based on coordinate convolution
TL;DR: The “coordinate convolution” is proposed,” which can effectively extract local structural information of the point cloud, to solve the inapplicability of conventional convolution neural network structures on the 3D point cloud.
Posted Content
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
TL;DR: MTI-Net as discussed by the authors explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit and propagates distilled task information from lower to higher scales via a feature propagation module.
Book ChapterDOI
Contra-Lateral Information CNN for Core Lesion Segmentation Based on Native CTP in Acute Stroke
TL;DR: A deep learning-based method to automatically segment necrotic brain tissue at the time of acute imaging based on CT perfusion (CTP) imaging, using a convolutional neural network to make a voxelwise segmentation of the core lesion.
Journal ArticleDOI
Stable polyp-scene classification via subsampling and residual learning from an imbalanced large dataset.
Hayato Itoh,Holger R. Roth,Masahiro Oda,Masashi Misawa,Yuichi Mori,Shin-ei Kudo,Kensaku Mori,Kensaku Mori +7 more
TL;DR: An efficient and balanced learning technique for deep residual learning that achieves stable polyp-scene classification with low false positive (FP) detection and post-processing reduces the FPs that occur in the practical application of polyp -scene classification.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Related Papers (5)
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more