CVPR 2018 论文分享会

Deep Learning Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization Abstract Global covarian...

2018-05-12 15:51:38

阅读数 2244

评论数 2

CVPR 2018 目标检测(Object Detection)

Cascade R-CNN: Delving into High Quality Object Detection In object detection, an intersection over union (IoU) threshold is required to define posi...

2018-04-19 21:02:52

阅读数 11490

评论数 0

目标检测算法对比

R-CNN。 来自 ICCV 2015,可以说是利用深度学习进行目标检测的开山之作。作者Ross Girshick多次在PASCAL VOC的目标检测竞赛中折桂,2010年更带领团队获得终身成就奖,如今供职于Facebook旗下的FAIR。这篇文章思路简洁,在DPM方法多年平台期后,效果提高显著...

2018-04-14 21:49:58

阅读数 23799

评论数 1

卷积网络架构对比

在卷积网络领域有几个有名字的架构。最常见的是: LeNet。卷积网络的第一个成功应用是由Yann LeCun在20世纪90年代开发的。其中最著名的是用于读取zip编码,数字等的LeNet架构。 本文的主要内容是通过更多地依赖于自动学习来建立更好的模式识别系统, 减少手工设计的启发式学习...

2018-04-11 23:18:26

阅读数 1268

评论数 0

基于反向传播的多层神经网络训练原理

原文地址请猛戳这里 该项目描述了采用反向传播算法的多层神经网络学习过程。为了说明这一过程, 使用两个输入层和一个输出层的三层神经网络, 如下图所示: 每个神经元由两个单元组成。第一单元添加权重系数和输入值的产出。第二单元实现非线性函数, 称为神经元激活函数。ee e 是加法器输出值...

2018-03-30 16:16:57

阅读数 790

评论数 0

视觉识别:CS231n卷积神经网络

原译文地址请猛戳这里 目录: 架构概述 卷积网络层 卷积层 池化层 归一化层 全连接层 将全连接层转换为卷积层 卷积网络架构 层模式 层大小模式 案例研究LeNet AlexNet ZFNet GoogLeNet VGGNet 计算考虑 其他参考 ...

2018-02-02 17:06:43

阅读数 1018

评论数 0

论文阅读笔记(五十六):Image Super-Resolution Using Deep Convolutional Networks

Abstract—We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/h...

2018-05-18 20:12:58

阅读数 561

评论数 1

论文阅读笔记(五十五):Self-Normalizing Neural Networks

Abstract Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural netwo...

2018-05-18 18:07:56

阅读数 267

评论数 0

论文阅读笔记(五十四):V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Abstract. Convolutional Neural Networks (CNNs) have been recently employed to solve problems from both the computer vision and medical image analysis...

2018-05-14 23:52:45

阅读数 1729

评论数 0

论文阅读笔记(五十三):Understanding Deep Convolutional Networks

Abstract Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems. We review...

2018-05-14 16:19:00

阅读数 249

评论数 0

论文阅读笔记(五十二):Outline Objects using Deep Reinforcement Learning

Abstract. Image segmentation needs both local boundary position information and global object context information. The performance of the recent stat...

2018-05-14 16:08:55

阅读数 285

评论数 0

论文阅读笔记(五十一):Understanding Deep Image Representations by Inverting Them

Abstract Image representations, from SIFT and Bag of Visual Words to Convolutional Neural Networks (CNNs), are a crucial component of almost any ima...

2018-05-14 15:43:14

阅读数 536

评论数 0

论文阅读笔记(四十九):3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Pr..

Abstract—We propose a method based on deep learning to perform cardiac segmentation on short axis MRI image stacks iteratively from the top slice (ar...

2018-05-13 19:46:18

阅读数 183

评论数 0

论文阅读笔记(四十八):3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

Abstract. This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attract...

2018-05-13 17:39:18

阅读数 1603

评论数 0

基于卷积神经网络的不良地质体识别与分类

在泛函分析中,卷积、旋积或摺积(英语:Convolution)是通过两个函数f 和g 生成第三个函数的一种数学算子,表征函数f 与g经过翻转和平移的重叠部分的面积。 如果将参加卷积的一个函数看作区间的指示函数,卷积还可以被看作是“滑动平均”的推广。 地震勘探中,在地表激发点激发的地震子波(se...

2018-05-12 17:18:24

阅读数 342

评论数 0

论文阅读笔记(四十七):Attention Is All You Need

Abstract The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a dec...

2018-05-12 16:17:19

阅读数 1014

评论数 0

论文阅读笔记(四十六):Generative Adversarial Nets

Abstract We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a gene...

2018-05-12 16:06:30

阅读数 523

评论数 0

论文阅读笔记(四十五):Deformable Convolutional Networks

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their buildin...

2018-05-07 00:55:31

阅读数 352

评论数 0

论文阅读笔记(四十四):Deconvolutional Networks

Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors s...

2018-05-06 20:59:28

阅读数 632

评论数 0

论文阅读笔记(四十三):Adaptive Deconvolutional Networks for Mid and High Level Feature Learning

We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained ...

2018-05-06 01:24:45

阅读数 164

评论数 0

提示
确定要删除当前文章?
取消 删除
关闭
关闭