3,885 Hits in 8.8 sec

Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation [article]

Zhicheng Yan, Hao Zhang, Yangqing Jia, Thomas Breuel, Yizhou Yu
2016 arXiv   pre-print
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs).  ...  Furthermore, we integrate ReNet layers with FCNs, and develop a novel Hybrid deep ReNet (H-ReNet).  ...  Second, we construct a hybrid network (i.e. H-ReNet) by appending recurrent layers on top of FCNs.  ... 
arXiv:1603.04871v1 fatcat:yqiashtxivac5dk22zaeqfeqzu

Multimodal Recurrent Neural Networks With Information Transfer Layers for Indoor Scene Labeling

Abrar H. Abdulnabi, Bing Shuai, Zhen Zuo, Lap-Pui Chau, Gang Wang
2018 IEEE transactions on multimedia  
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps.  ...  It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modality  ...  This work is supported by the research grant for ADSC from A*STAR.  ... 
doi:10.1109/tmm.2017.2774007 fatcat:ckeq5rvofnavfckmeumtxvm2la

Fabric Defect Detection Using Activation Layer Embedded Convolutional Neural Network

Wenbin Ouyang, Jue Hou, Bugao Xu, Xiaohui Yuan
2019 IEEE Access  
A novel pairwise-potential activation layer was introduced to a CNN, leading to high accuracy of defect segmentation on fabrics with intricate features and imbalanced dataset.  ...  generation, and convolutional neural networks (CNNs).  ...  Recently, convolutional neural networks (CNN) have been demonstrated for effective image semantic segmentation [16] . The CNNs, e.g.  ... 
doi:10.1109/access.2019.2913620 fatcat:6h6o4f6fbfcg7ekwsxmk3j5u3a


S. Shajun Nisha, M. Nagoor Meeral, M. Mohamed Sathik
2022 International Journal of Health Sciences  
The primary intention concerning the proposed segmentation network is to categorize 7 retinal layers and fluid as distinct classes.  ...  This model was assessed over the public Duke dataset and the outputs demonstrate that this model attains a dice coefficient of 0.9.  ...  Kugelman et al [29] developed the recurrent neural network on the basis of graph search for delineating the retinal layers from normal and AMD images and it yields better accuracy.  ... 
doi:10.53730/ijhs.v6ns1.5009 fatcat:xpxrvj6c4bcnznrldicaji5u4e

Survey on Semantic Segmentation using Deep Learning Techniques

Fahad Lateef, Yassine Ruichek
2019 Neurocomputing  
Semantic segmentation is a challenging task in computer vision systems.  ...  Finally, we conclude by discussing some of the open problems and their possible solutions.  ...  ACKNOWLEDGMENT The authors express their gratitude to University Technology Belfort-Montbeliard and Higher Education Commission of Pakistan for providing the support and necessary requirement for completion  ... 
doi:10.1016/j.neucom.2019.02.003 fatcat:aelsfl7unvdw5j2rtyqhtgqrsm

Channel Max Pooling Layer for Fine-Grained Vehicle Classification [article]

Zhanyu Ma, Dongliang Chang, Xiaoxu Li
2020 arXiv   pre-print
Therefore, we propose a new layer which is placed between fully connected layers and convolutional layers, called as Chanel Max Pooling.  ...  The proposed layer groups the features map first and then compress each group into a new feature map by computing maximum of pixels with same positions in the group of feature maps.  ...  [8] propose a recurrent attention convolutional neural network for fine-grained recognition, which recursively learns discriminative region attention and region-based feature representation at multiple  ... 
arXiv:1902.11107v2 fatcat:ksw7v7iv7zauljb3miq7b6pyei

R2U++: a multiscale recurrent residual U-Net with dense skip connections for medical image segmentation

Mehreen Mubashar, Hazrat Ali, Christer Grönlund, Shoaib Azmat
2022 Neural computing & applications (Print)  
AbstractU-Net is a widely adopted neural network in the domain of medical image segmentation.  ...  The increased field of view with these blocks aids in extracting crucial features for segmentation which is proven by improvement in the overall performance of the network. (2) The semantic gap between  ...  The authors declare no conflict of interest. VII. REFERENCES  ... 
doi:10.1007/s00521-022-07419-7 pmid:35694048 pmcid:PMC9165712 fatcat:6i4ichwodzgrfoqf4dlwhxjagu

Optimized chest X-ray image semantic segmentation networks for COVID-19 early detection

Anandbabu Gopatoti, P. Vijayalakshmi
2022 Journal of X-Ray Science and Technology  
METHODS: For semantically segmenting infected lung lobes in CXR images for COVID-19 early detection, three structurally different deep learning (DL) networks such as SegNet, U-Net and hybrid CNN with SegNet  ...  Further, the optimized CXR image semantic segmentation networks such as GWO SegNet, GWO U-Net, and GWO hybrid CNN are developed with the grey wolf optimization (GWO) algorithm.  ...  Hybrid CNN architecture The CNN hybridization is formed by combining SegNet and U-Net architectures with downsampling and upsampling properties for conducting semantic segmentation of COVID-19 CXR images  ... 
doi:10.3233/xst-211113 pmid:35213339 fatcat:flrz76hj4fazppwv3x4invs5v4

Fully Convolutional Networks for Semantic Segmentation [article]

Evan Shelhamer, Jonathan Long, Trevor Darrell
2016 arXiv   pre-print
We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations.  ...  We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.  ...  ACKNOWLEDGEMENTS This work was supported in part by DARPA's MSEE and SMISC programs, NSF awards IIS-1427425, IIS-1212798, IIS-1116411, and the NSF GRFP, Toyota, and the Berkeley Vision and Learning Center  ... 
arXiv:1605.06211v1 fatcat:gls74fuavrgsfaqpwgdx6ycjee

U-Net and its variants for Medical Image Segmentation : A short review [article]

Vinay Ummadi
2022 arXiv   pre-print
The paper is a short review of medical image segmentation using U-Net and its variants.  ...  Segmenting out the regions of interest has significant importance in medical images and is key for diagnosis. This paper also gives a bird eye view of how medical image segmentation has evolved.  ...  Trans U-Net [2] is a hybrid network of U-Net and visual transformer that has attention modules.  ... 
arXiv:2204.08470v1 fatcat:me5mmiu6qvbyfedzlug67mj2ka

Automatic Deep Learning Semantic Segmentation of Ultrasound Thyroid Cineclips using Recurrent Fully Convolutional Networks

Jeremy M. Webb, Duane D. Meixner, Shaheeda A. Adusei, Eric C. Polley, Mostafa Fatemi, Azra Alizad
2020 IEEE Access  
We demonstrate the potential application of convolutional LSTM models for thyroid ultrasound segmentation.  ...  In this paper, we exploit time sequence information using a novel spatio-temporal recurrent deep learning network to automatically segment the thyroid gland in ultrasound cineclips.  ...  ACKNOWLEDGMENT The authors thank Barbara Foreman and Julie Simonson, their clinical coordinators, for patient recruitment as well as Erin Jarrod and Jennifer Poston for administrative support.  ... 
doi:10.1109/access.2020.3045906 pmid:33747681 pmcid:PMC7978237 fatcat:gevpksgrwndixclnzvr4p4j7au

Fully Connected Pyramid Pooling Network (FCPPN) – A Method For Brain Tumor Segmentation

2019 International Journal of Engineering and Advanced Technology  
These methods are used to predicate the tumor.Our paper proposes a new architecture called FCPPNET which is a hybrid combination of FCN and PSPNET.  ...  Semantic Segmentation is mainly used in the area of medical imaging. It is mainly used for the doctors to identify the tumor in a clear and exact way.  ...  Finally, these layers are connected at the end of Softmax Layers [20] . Zhao,Hengshuang,et al [21] deals with the deep convolutional network for semantic segmentation.  ... 
doi:10.35940/ijeat.a1658.109119 fatcat:w47h3h6xbbb55acbykp5ih32qm


2021 Zenodo  
selecting a relevant set of features to make ease the classification process.  ...  In this context, Multi-layer preceptor-based back propagation is introduced for detecting misbehavior activities attained in the lane-line image.  ...  Qin Zou, et al [20] have combined recurrent neural network (RNN) and convolutional neural network (CNN) for the lane prediction process.  ... 
doi:10.5281/zenodo.6817816 fatcat:q3fnsof3kjashap7msddddqavy

Cardiac Segmentation from MRI images using Recurrent &Residual Convolutional Neural Network based on SegNet and Level Set methods

Mikkili Dileep Kumar, Dr. K V Ramana, Dr. G. Madhavi
2021 Zenodo  
Second, the use of recurrent residual convolutional layers ensures that the relevant features retrieved to perform the segmentation tasks.  ...  ResNet consists of a layer and it has taken inputs involving multiple layers of the neural network, giving precise performance.  ...  A hybrid model called R-SegNet is made with the combination of ResNet and SegNet.  ... 
doi:10.5281/zenodo.4491839 fatcat:tqb2hg656vbdfkalw6drokmo5a

Shelf Commodity Identification Method Based on Hybrid Fully Convolutional Automatic Encoder

Aofeng Cheng, Guodong Chen, Zheng Wang
2019 IEEE Access  
At present, the semantic information segmentation algorithms mainly include FCN (Fully Convolutional Network), PSPNet (Pyramid Scene Parsing Network), Deeplab and so on.  ...  In view of the inadequate results of features extracted by these algorithms from RGB image, a hybrid fully convolutional autoencoder neural network (HFCAN) structure, which introduces fully convolutional  ...  ACKNOWLEDGMENT (Aofeng Cheng and Guodong Chen are co-first authors.)  ... 
doi:10.1109/access.2019.2955560 fatcat:uwshcxv5zjbblfud34jidc7leq
« Previous Showing results 1 — 15 out of 3,885 results