【论文推荐】最新5篇深度学习相关论文推介——感知度量、图像检索、联合视盘和视杯分割、谱聚类、MPI并行

【导读】专知内容组整理了最近人工智能领域相关期刊的5篇最新综述文章,为大家进行介绍,欢迎查看!

1. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (深度特征在感知度量中难以置信的有效性)



作者: Richard Zhang,Phillip Isola,Alexei A. Efros,Eli Shechtman,Oliver Wang

摘要:While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on the ImageNet classification task has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are critical for their success? To answer these questions, we introduce a new Full Reference Image Quality Assessment (FR-IQA) dataset of perceptual human judgments, orders of magnitude larger than previous datasets. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by huge margins. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.

期刊:arXiv, 1 月 12 日

网址

http://www.zhuanzhi.ai/document/55a5ec8a7580cbe74a6f64e11df39d9b

2. DeepSeek: Content Based Image Search & Retrieval(DeepSeek:基于内容的图像检索)



作者: Tanya Piplani,David Bamman

摘要:Most of the internet today is composed of digital media that includes videos and images. With pixels becoming the currency in which most transactions happen on the internet, it is becoming increasingly important to have a way of browsing through this ocean of information with relative ease. YouTube has 400 hours of video uploaded every minute and many million images are browsed on Instagram, Facebook, etc. Inspired by recent advances in the field of deep learning and success that it has gained on various problems like image captioning and, machine translation , word2vec , skip thoughts, etc, we present DeepSeek a natural language processing based deep learning model that allows users to enter a description of the kind of images that they want to search, and in response the system retrieves all the images that semantically and contextually relate to the query. Two approaches are described in the following sections.

期刊:arXiv, 1 月 11 日

网址

http://www.zhuanzhi.ai/document/2261ccce9805813790a943597a6c73fe

3. Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation(基于多标签深度网络和极性变换的联合视盘和视杯分割)



作者: Huazhu Fu,Jun Cheng,Yanwu Xu,Damon Wing Kee Wong,Jiang Liu,Xiaochun Cao

摘要:Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, the accurate and automatic segmentation of optic disc (OD) and optic cup (OC) from fundus images is a fundamental task. Most existing methods segment them separately, and rely on hand-crafted visual feature from fundus images. In this paper, we propose a deep learning architecture, named M-Net, which solves the OD and OC segmentation jointly in a one-stage multi-label system. The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function. The multi-scale input layer constructs an image pyramid to achieve multiple level receptive field sizes. The U-shape convolutional network is employed as the main body network structure to learn the rich hierarchical representation, while the side-output layer acts as an early classifier that produces a companion local prediction map for different scale layers. Finally, a multi-label loss function is proposed to generate the final segmentation map. For improving the segmentation performance further, we also introduce the polar transformation, which provides the representation of the original image in the polar coordinate system. The experiments show that our M-Net system achieves state-of-the-art OD and OC segmentation result on ORIGA dataset. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated CDR value on both ORIGA and SCES datasets.

期刊:arXiv, 1 月 11日

网址

http://www.zhuanzhi.ai/document/fff712a31d01bbe1e5c10665653dfca4/

4. SpectralNet:Spectral Clustering using Deep Neural Networks (SpectralNet:使用深度神经网络的谱聚类)



作者: Uri Shaham,Kelly Stanton,Henry Li,Boaz Nadler,Ronen Basri,Yuval Kluger

摘要:Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e., out-of-sample-extension). In this paper we introduce a deep learning approach to spectral clustering that overcomes the above shortcomings. Our network, which we call SpectralNet, learns a map that embeds input data points into the eigenspace of their associated graph Laplacian matrix and subsequently clusters them. We train SpectralNet using a procedure that involves constrained stochastic optimization. Stochastic optimization allows it to scale to large datasets, while the constraints, which are implemented using a special-purpose output layer, allow us to keep the network output orthogonal. Moreover, the map learned by SpectralNet naturally generalizes the spectral embedding to unseen data points. To further improve the quality of the clustering, we replace the standard pairwise Gaussian affinities with affinities leaned from unlabeled data using a Siamese network. Additional improvement can be achieved by applying the network to code representations produced, e.g., by standard autoencoders. Our end-to-end learning procedure is fully unsupervised. In addition, we apply VC dimension theory to derive a lower bound on the size of SpectralNet. State-of-the-art clustering results are reported on the Reuters dataset. Our implementation is publicly available at https://github.com/kstant0725/SpectralNet .

期刊:arXiv, 1 月 10日

网址

http://www.zhuanzhi.ai/document/e624265c1b91d3ad0620ebcf26d194e9

5. MXNET-MPI: Embedding MPI parallelism in Parameter Server Task Model for scaling Deep Learning(MXNET-MPI:scaling深度学习在参数服务器任务模型中的嵌入MPI并行)



作者: Amith R Mamidala,Georgios Kollias,Chris Ward,Fausto Artico

摘要:Existing Deep Learning frameworks exclusively use either Parameter Server(PS) approach or MPI parallelism. In this paper, we discuss the drawbacks of such approaches and propose a generic framework supporting both PS and MPI programming paradigms, co-existing at the same time. The key advantage of the new model is to embed the scaling benefits of MPI parallelism into the loosely coupled PS task model. Apart from providing a practical usage model of MPI in cloud, such framework allows for novel communication avoiding algorithms that do parameter averaging in Stochastic Gradient Descent(SGD) approaches. We show how MPI and PS models can synergestically apply algorithms such as Elastic SGD to improve the rate of convergence against existing approaches. These new algorithms directly help scaling SGD clusterwide. Further, we also optimize the critical component of the framework, namely global aggregation or allreduce using a novel concept of tensor collectives. These treat a group of vectors on a node as a single object allowing for the existing single vector algorithms to be directly applicable. We back our claims with sufficient emperical evidence using large scale ImageNet 1K data. Our framework is built upon MXNET but the design is generic and can be adapted to other popular DL infrastructures.

期刊:arXiv, 1 月 12 日

网址

http://www.zhuanzhi.ai/document/dcc9fde2f633561366d502be61dace5e

原文发布于微信公众号 - 专知(Quan_Zhuanzhi)

原文发表时间:2018-01-16

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏CreateAMind

awesome-self-supervised-learning papers

https://github.com/jason718/awesome-self-supervised-learning

34020
来自专栏CVer

最新的46篇CV论文!

计算机视觉论文速递系列推文目前是一周一次,因为Amusi说过很多次,这个系列文章整理到公众号上有点"吃"时间。所以暂时将原来的日报形式改成周报的形式。

41820
来自专栏专知

【论文推荐】最新六篇机器翻译相关论文— 自注意力残差解码器、SGNMT、级联方法、神经序列预测、Benchmark、人类水平

【导读】专知内容组整理了最近六篇机器翻译(Machine Translation)相关文章,为大家进行介绍,欢迎查看! 1.Self-Attentive Res...

38270
来自专栏专知

【论文推荐】最新八篇图像检索相关论文—三元组、深度特征图、判别式、卷积特征聚合、视觉-关系知识图谱、大规模图像检索

35130
来自专栏专知

【论文推荐】最新四篇CVPR2018 视频描述生成相关论文—双向注意力、Transformer、重构网络、层次强化学习

【导读】专知内容组在昨天推出八篇视频描述生成(Video Captioning)相关文章,今天为大家推出CVPR2018最新视频描述生成相关论文,欢迎查看!

36020
来自专栏专知

【论文推荐】最新八篇图像描述生成相关论文—比较级对抗学习、正则化RNNs、深层网络、视觉对话、婴儿说话、自我检索

【导读】专知内容组整理了最近八篇图像描述生成(Image Captioning)相关文章,为大家进行介绍,欢迎查看! 1.Generating Diverse ...

548100
来自专栏AI研习社

126篇殿堂级深度学习论文分类整理 从入门到应用(上)

█ 如果你有非常大的决心从事深度学习,又不想在这一行打酱油,那么研读大牛论文将是不可避免的一步。而作为新人,你的第一个问题或许是:“论文那么多,从哪一篇读起?”...

36880
来自专栏专知

【论文推荐】最新六篇视频分类相关论文—层次标签推断、知识图谱、CNNs、DAiSEE、表观和关系网络、转移学习

【导读】专知内容组整理了最近六篇视频分类(Video Classification)相关文章,为大家进行介绍,欢迎查看! 1. Hierarchical Lab...

54350
来自专栏专知

【专知荟萃15】图像检索Image Retrieval知识资料全集(入门/进阶/综述/视频/代码/专家,附PDF下载)

图像检索(Image Retrieval)专知荟萃 入门学习 进阶文章 综述 Tutorial 视频教程 代码 领域专家 Datasets 入门学习 相似...

986100
来自专栏CreateAMind

GAN论文解读推荐

ICLR 2017 的 submission DDL 刚刚过,网上就纷纷有了 ICLR 2017 导读的文章。本周我也将为大家带来 ICLR 2017 subm...

23730

扫码关注云+社区

领取腾讯云代金券