Wide and deep volumetric residual networks for volumetric image classification
نویسندگان
چکیده
3D shape models that directly classify objects from 3D information have become more widely implementable. Current state of the art models rely on deep convolutional and inception models that are resource intensive. Residual neural networks have been demonstrated to be easier to optimize and do not suffer from vanishing/exploding gradients observed in deep networks. Here we implement a residual neural network for 3D object classification of the 3D Princeton ModelNet dataset. Further, we show that widening network layers dramatically improves accuracy in shallow residual nets, and residual neural networks perform comparable to state-of-the-art 3D shape net models, and we show that widening network layers improves classification accuracy. We provide extensive training and architecture parameters providing a better understanding of available network architectures for use in 3D object classification.
منابع مشابه
On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task
Deep convolutional neural networks are powerful tools for learning visual representations from images. However, designing efficient deep architectures to analyse volumetric medical images remains challenging. This work investigates efficient and flexible elements of modern convolutional networks such as dilated convolution and residual connection. With these essential building blocks, we propos...
متن کاملVolumetric soil moisture estimation using Sentinel 1 and 2 satellite images
Surface soil moisture is an important variable that plays a crucial role in the management of water and soil resources. Estimating this parameter is one of the important applications of remote sensing. One of the remote sensing techniques for precise estimation of this parameter is data-driven models. In this study, volumetric soil moisture content was estimated using data-driven models, suppor...
متن کاملCardiovascular Edge Detection using Neural Networks
In order to perform computational fluid dynamics simulations of blood flows in patients, models of their cardiovascular system are required. Currently the only way to obtain models of sufficient quality is for practitioners to manually construct them from volumetric scan data using computer aided design (CAD) software. In order to automate the process of cardiovascular model construction it is ...
متن کاملA Deep Model for Super-resolution Enhancement from a Single Image
This study presents a method to reconstruct a high-resolution image using a deep convolution neural network. We propose a deep model, entitled Deep Block Super Resolution (DBSR), by fusing the output features of a deep convolutional network and a shallow convolutional network. In this way, our model benefits from high frequency and low frequency features extracted from deep and shallow networks...
متن کاملPorosity classification from thin sections using image analysis and neural networks including shallow and deep learning in Jahrum formation
The porosity within a reservoir rock is a basic parameter for the reservoir characterization. The present paper introduces two intelligent models for identification of the porosity types using image analysis. For this aim, firstly, thirteen geometrical parameters of pores of each image were extracted using the image analysis techniques. The extracted features and their corresponding pore types ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1710.01217 شماره
صفحات -
تاریخ انتشار 2017