文档章节

人工智能资料库:第45辑(20170418)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:19
字数 890
阅读 2
收藏 0

1.【论文 & 代码】The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

简介:

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions.

Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train.

In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid
and Gatech 1 , without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets.

原文链接:https://github.com/0bserver07/One-Hundred-Layers-Tiramisu

论文链接:https://arxiv.org/abs/1611.09326


2.【博客】Explanation of One-shot Learning with Memory-Augmented Neural Networks

简介:

I've found that the overwhelming majority of online information on artificial intelligence research falls into one of two categories: the first is aimed at explaining advances to lay audiences, and the second is aimed at explaining advances to other researchers. I haven't found a good resource for people with a technical background who are unfamiliar with the more advanced concepts and are looking for someone to fill them in. This is my attempt to bridge that gap, by providing approachable yet (relatively) detailed explanations. In this post, I explain the titular paper - One-shot Learning with Memory-Augmented Neural Networks.

原文链接:http://rylanschaeffer.github.io/content/research/one_shot_learning_with_memory_augmented_nn/main.html


3.【博客】Medical Image Analysis with Deep Learning 

简介:


Analyzing images and videos, and using them in various applications such as self driven cars, drones etc. with underlying deep learning techniques has been the new research frontier. The recent research papers such as “A Neural Algorithm of Artistic Style”, show how a styles can be transferred from an artist and applied to an image, to create a new image. Other papers such as “Generative Adversarial Networks” (GAN) and “Wasserstein GAN” have paved the path to develop models that can learn to create data that is similar to data that we give them. Thus opening up the world to semi-supervised learning and paving the path to a future of unsupervised learning.

原文链接:http://www.kdnuggets.com/2017/03/medical-image-analysis-deep-learning.html


4.【论文 & 代码】Conditional Similarity Networks

简介:


What makes images similar? To measure the similarity between images, they are typically embedded in a featurevector space, in which their distance preserve the relative dissimilarity. However, when learning such similarity embeddings the simplifying assumption is commonly made that images are only compared to one unique measure of similarity. A main reason for this is that contradicting notions of similarities cannot be captured in a single space. To address this shortcoming, we propose Conditional Similarity Networks (CSNs) that learn embeddings differentiated into semantically distinct subspaces that capture the different notions of similarities. CSNs jointly learn a disentangled embedding where features for different similarities are encoded in separate dimensions as well as masks that select and reweight relevant dimensions to induce a subspace that encodes a specific similarity notion. We show that our approach learns interpretable image representations with visually relevant semantic subspaces. Further, when evaluating on triplet questions from multiple similarity notions our model even outperforms the accuracy obtained by training individual specialized networks for each notion separately.

原文链接:https://github.com/andreasveit/conditional-similarity-networks

论文链接:https://arxiv.org/pdf/1603.07810.pdf


5.【博客】Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis

简介:


We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution – but complete – output. To this end, we introduce a 3D-EncoderPredictor Network (3D-EPN) which is composed of 3D convolutional layers. The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space. This allows us to predict global structure in unknown areas at high accuracy. We then correlate these intermediary results with 3D geometry from a shape database at test time. In a final pass, we propose a patch-based 3D shape synthesis method that imposes the 3D geometry from these retrieved shapes as constraints on the coarsely-completed mesh. This synthesis process enables us to reconstruct finescale detail and generate high-resolution output while respecting the global mesh structure obtained by the 3D-EPN. Although our 3D-EPN outperforms state-of-the-art completion method, the main contribution in our work lies in the combination of a data-driven shape predictor and analytic 3D shape synthesis. In our results, we show extensive evaluations on a newly-introduced shape completion benchmark for both real-world and synthetic data.

原文链接:http://graphics.stanford.edu/projects/cnncomplete/


本文转载自:http://www.jianshu.com/p/72cbdbf69928

共有 人打赏支持
AllenOR灵感
粉丝 11
博文 2635
码字总数 83001
作品 0
程序员
私信 提问
MySQL XtraBackup 备份

备注:先安装XtraBackup 下载地址:https://www.percona.com/downloads/XtraBackup/LATEST/ 此处我的版本是:percona-xtrabackup-24-2.4.6-2.el7.x8664.rpm 本地安装: yum localinstall per......

Lydialyd
2018/06/26
0
0
Aruba AC如何通过CLI备份及导入导出

通过CLI登录Aruba AC。Aruba AC是通过SSH加密的,因此建议使用PUTTY或者Xshell等支持SSH的终端工具。导入导出需要使用到tftp server,请先与本地建立tftp server. 1.配置文档备份 备份之前,先...

Fonphxion
2017/04/18
0
0
MySQL XtraBackup安装备份

备注:先安装XtraBackup 下载地址:https://www.percona.com/downloads/XtraBackup/LATEST/ 此处我的版本是:percona-xtrabackup-24-2.4.6-2.el7.x8664.rpm 本地安装: yum localinstall per......

Lydialyd
2018/06/26
0
0
android获取服务器mp4资源抛出412错误

产品的ios端和android同时获取同一个mp4视频资源,android会报出412错误,IOS端正常播放,andorid端播放wmv视频正常 android日志信息如下: /VLC/PlaybackService: Loading position 0 in org.v...

BaymaxCssy
2017/11/07
179
0
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0

没有更多内容

加载失败,请刷新页面

加载更多

Jmeter参数的AES加密使用

在Jmeter日常实践中,大家应该都遇到过接口传参需要加密的情况。以登陆为例,用户名和密码一般都需要进行加密传输,在服务端再进行解密,这样安全系数会更高,但在使用jmeter进行接口测试的时...

程序猿拿Q
27分钟前
2
0
MYSQL 日期函数 Date and Time Functions

Table 12.13 Date and Time Functions Name Description ADDDATE() Add time values (intervals) to a date value ADDTIME() Add time CONVERT_TZ() Convert from one time zone to another ......

_liucui_
34分钟前
2
0
Android代码混淆ProGuard工作原理简介

ProGuard能够对Java类中的代码进行压缩(Shrink),优化(Optimize),混淆(Obfuscate),预检(Preveirfy)。    1. 压缩(Shrink): 在压缩处理这一步中,用于检测和删除没有使用的类,字段...

SuShine
36分钟前
1
0
Idea 2018激活

教程地址: https://www.52pojie.cn/thread-781394-1-1.html 亲测可用

一个不正经的程序员
42分钟前
1
0
Android组件化开发实践和案例分享

目录介绍 1.为什么要组件化 1.1 为什么要组件化 1.2 现阶段遇到的问题 2.组件化的概念 2.1 什么是组件化 2.2 区分模块化与组件化 2.3 组件化优势好处 2.4 区分组件化和插件化 2.5 applicatio...

潇湘剑雨
42分钟前
0
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部