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 10
博文 2635
码字总数 83001
作品 0
程序员
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
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
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
06/26
0
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0

没有更多内容

加载失败,请刷新页面

加载更多

linux 系统的运行级别

运行级别 运行级别 | 含义 0 关机 1 单用户模式,可以想象为windows 的安全模式,主要用于修复系统 2 不完全的命令模式,不含NFS服务 3 完全的命令行模式,就是标准的字符界面 4 系统保留 5 ...

Linux学习笔记
今天
2
0
学习设计模式——命令模式

任何模式的出现,都是为了解决一些特定的场景的耦合问题,以达到对修改封闭,对扩展开放的效果。命令模式也不例外: 命令模式是为了解决命令的请求者和命令的实现者之间的耦合关系。 解决了这...

江左煤郎
今天
3
0
字典树收集(非线程安全,后续做线程安全改进)

将500W个单词放进一个数据结构进行存储,然后进行快速比对,判断一个单词是不是这个500W单词之中的;来了一个单词前缀,给出500w个单词中有多少个单词是该前缀. 1、这个需求首先需要设计好数据结...

算法之名
昨天
14
0
GRASP设计模式

此文参考了这篇博客,建议读者阅读原文。 面向对象(Object-Oriented,OO)是当下软件开发的主流方法。在OO分析与设计中,我们首先从问题领域中抽象出领域模型,在领域模型中以适当的粒度归纳...

克虏伯
昨天
1
0
Coding and Paper Letter(四十)

资源整理。 1 Coding: 1.Tomislav Hengl撰写的非官方作者指南:Michael Gould•Wouter Gerritsma。 UnofficialGuide4Authors 2.R语言包rwrfhydro,社区贡献的工具箱,用于管理,分析和可视化...

胖胖雕
昨天
1
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