__Sunshine__-CSDN博客

原创 CVPR 2018 论文分享会

Deep LearningTowards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root NormalizationAbstract Global covariance pooling in convolutional neural networks has ach...

2018-05-12 15:51:38 4225 2

原创 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 positives and negatives. An object detector, trained wi...

2018-04-19 21:02:52 14134

原创目标检测算法对比

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。包括本文在内的一系列目标检测算法：RCNN, Fast RCNN, Faster RCNN代表当下目...

2018-04-14 21:49:58 45227

原创卷积网络架构对比

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。展示了手工制作的特征提取可以用精心设计的直接在像素图像上操作的学习机器来代替。综述了手写体字符识...

2018-04-11 23:18:26 2474

翻译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, y=f(e)y=f(e) y = f (e) 是非线性元件的输出值。yy y 也是神经元的输出...

2018-03-30 16:16:57 2491 1

翻译视觉识别：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计算考虑其他参考卷积神经网络(CNNs / ConvNets)卷积神经网络与上一章中的普通神经网络非常相似：它们

2018-02-02 17:06:43 1551

原创论文阅读笔记（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/high-resolution images. The mapping is represented a...

2018-05-18 20:12:58 2581 1

原创论文阅读笔记（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 networks (RNNs). However, success stories of Deep Learni...

2018-05-18 18:07:56 734

原创论文阅读笔记（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 fields. Despite their popularity, most approaches ...

2018-05-14 23:52:45 7200

原创论文阅读笔记（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 their architecture, which scatters data with a cas...

2018-05-14 16:19:00 1091

原创论文阅读笔记（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 state-of-the-art method, fully convolutional networks, ...

2018-05-14 16:08:55 803

原创论文阅读笔记（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 image understanding system. Nevertheless, our understa...

2018-05-14 15:43:14 2804

原创论文阅读笔记（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 (around the base) to the bottom slice (around the apex...

2018-05-13 19:46:18 1341

原创论文阅读笔记（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 attractive use cases of this method: (1) In a semi-automat...

2018-05-13 17:39:18 4077

原创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(seismic wavelet)向地下传播,当遇到地下波阻抗界面时,一部分能量就会作为反射地震波向上反射回...

2018-05-12 17:18:24 1566

原创论文阅读笔记（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 decoder. The best performing models also connect the e...

2018-05-12 16:17:19 4300 2

原创论文阅读笔记（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 generative model G that captures the data distribution,...

2018-05-12 16:06:30 2230

原创论文阅读笔记（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 building modules. In this work, we introduce two new modul...

2018-05-07 00:55:31 2548

原创论文阅读笔记（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 spatially pool edge information which destroys cues ...

2018-05-06 20:59:28 1722

原创论文阅读笔记（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 on natural images, the layers of our model capture ...

2018-05-06 01:24:45 2538

原创论文阅读笔记（四十二）：Visualizing and Understanding Convolutional Networks

Abstract. Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. However there is no clear understanding...

2018-05-05 22:08:26 1149 1

原创论文阅读笔记（四十一）：U-Net: Convolutional Networks for Biomedical Image Segmentation

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 t...

2018-05-05 11:36:20 2222

原创论文阅读笔记（四十）：Learning Spatiotemporal Features with 3D Convolutional Networks（C3D）

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our fin...

2018-05-03 18:36:49 3049

原创论文阅读笔记（三十九）：3D Convolutional Neural Networks for Human Action Recognition

This model extracts features from both spatial and temporal dimensions by performing 3D convolutions, thereby capturing the motion information encoded in multiple adjacent frames. The developed model ...

2018-05-03 15:48:22 1338

原创论文阅读笔记（三十八）：Dynamic Zoom-in Network for Fast Object Detection in Large Images

We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detect...

2018-04-26 23:15:30 2430 1

原创论文阅读笔记（三十七）：MegDet: A Large Mini-Batch Object Detector

The development of object detection in the era of deep learning, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from novel network, new framework...

2018-04-24 23:18:49 3115

原创论文阅读笔记（三十六）：Single-Shot Refinement Neural Network for Object Detection

For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit t...

2018-04-24 22:49:10 1663 1

原创论文阅读笔记（三十五）：R-FCN-3000 at 30fps: Decoupling Detection and Classification

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness scor...

2018-04-23 23:12:19 544 1

原创论文阅读笔记（三十四）：An Analysis of Scale Invariance in Object Detection－SNIP

An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are compared by training th...

2018-04-23 23:00:45 839

原创论文阅读笔记（三十三）：Relation Network for Object Detection

Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-o...

2018-04-22 23:05:56 2569

原创论文阅读笔记（三十二）：Cascade R-CNN: Delving into High Quality Object Detection

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy dete...

2018-04-22 19:40:27 2980

原创论文阅读笔记（三十一）：DensePose: Dense Human Pose Estimation In The Wild

In this work, we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We first gather dense cor...

2018-04-22 16:41:03 7021 5

原创论文阅读笔记（三十一）：Data Distillation: Towards Omni-Supervised Learning

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-super...

2018-04-22 15:21:46 1302

原创论文阅读笔记（三十）：Learning to Segment Every Thing

Existing methods for object instance segmentation require all training instances to be labeled with segmentation masks. This requirement makes it expensive to annotate new categories and has restricte...

2018-04-22 12:29:38 954

原创论文阅读笔记（二十九）：Detecting and Recognizing Human-Object Interactions

To understand the visual world, a machine must not only recognize individual object instances but also how they interact. Humans are often at the center of such interactions and detecting human-object...

2018-04-22 12:08:50 1341

原创论文阅读笔记（二十八）：facebookresearch/Detectron

At FAIR, Detectron has enabled numerous research projects, including: Feature Pyramid Networks for Object DetectionFeature pyramids are a basic component in recognition systems for detecting objec...

2018-04-21 17:15:14 1419

原创论文阅读笔记（二十七）：Focal Loss for Dense Object Detection

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stag...

2018-04-21 16:41:19 687

原创论文阅读笔记（二十六）：Group Normalization

Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems — BN’s err...

2018-04-21 13:29:24 1713

原创论文阅读笔记（二十五）：Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate S

Training Deep Neural Networks is complicated by the fact that the distribution of each layer’s inputs changes during training, as the parameters of the previous layers change. This slows down the trai...

2018-04-21 10:15:02 253

原创论文阅读笔记（二十四）：Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for...

2018-04-19 22:54:06 3787 1

leetcode-常见考题4.pdf

leetcode-常见考题3.pdf

leetcode-常见考题2.pdf

leetcode-常见考题1.pdf

相机标定笔记.pdf

空空如也