机器学习、深度学习、计算机视觉、自然语言处理及应用案例——干货分享

机器学习、深度学习、计算机视觉、自然语言处理及应用案例——干货分享(持续更新……)


author@jason_ql
http://blog.csdn.net/lql0716


1、机器学习/深度学习

1.1 对抗生成网络GAN

【2017.04.21】

  • 对抗生成网络GAN变种大集合
    链接
  • 资源 | 生成对抗网络及其变体的论文汇总
    链接
  • 生成对抗网络(GAN)图片编辑
    链接
  • CycleGAN失败案例
    链接

【2017.04.22】

  • 用条件生成对抗网络玩转中文书法
    链接
  • 《Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking》F Juefei-Xu, V N Boddeti, M Savvides [CMU & Michigan State University] (2017)
    链接

【2017.04.23】

  • TP-GAN 让图像生成再获突破,根据单一侧脸生成正面逼真人脸
    链接】【GitHub】

【2017.04.26】

  • 【对抗生成网络GAN教程】
    《Tutorial on GANs》by Adit Deshpande
    【链接】【GitHub

【2017.05.07】

  • 【GAN相关资源与实现】’Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN’ by YadiraF
    【链接】【GitHub
  • 【PyTorch实现的CoGAN】《Coupled Generative Adversarial Networks》M Liu, O Tuzel [Mitsubishi Electric Research Labs (MERL)] (2016)
    链接】【GitHub
  • 【利用CGAN生成Sketch漫画】《Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks》Y Liu, Z Qin, Z Luo, H Wang [Beihang University & Samsung Telecommunication Research Institute] (2017)
    链接】【GitHub】
  • 《Adversarial Feature Learning》J Donahue, P Krähenbühl, T Darrell [UC Berkeley]
    链接】【GitHub
  • 【PyTorch实现的DCGAN、pix2pix、DiscoGAN、CycleGAN、BEGAN VAE、Neural Style Transfer、Char RNN等】’Paper Implementations - Use PyTorch to implement some classic frameworks’ by SunshineAtNoon
    【链接】【GitHub
  • 【GAN画风迁移】《Generative Adversarial Networks for Style Transfer (LIVE) - YouTube》by Siraj Raval
    【链接】【GitHub】【video

【2017.05.08】

  • 生成对抗网络(GAN)研究年度进展评述
    链接】【GitHub】
  • 【对抗生成网络(Gan)深入研究(文献/教程/模型/框架/库等)】《Delving deep into GANs》by Grigorios Kalliatakis
    链接】【GitHub
  • 【对抗式机器翻译】《Adversarial Neural Machine Translation》L Wu, Y Xia, L Zhao, F Tian, T Qin, J Lai, T Liu [Sun Yat-sen University & University of Science and Technology of China & Microsoft Research Asia] (2017)
    链接】【GitHub】
  • 【CycleGAN生成模型:熊变熊猫】’Models generated by CycleGAN’ by Tatsuya
    【链接】【GitHub
  • 【对抗生成网络(GAN)】《Generative Adversarial Networks (LIVE) - YouTube》by Siraj Raval
    【链接】【GitHub】【video
  • 【Keras实现的ACGAN/DCGAN】’Implementation of some basic GAN architectures in Keras’ by Batchu Venkat Vishal
    【链接】【GitHub

【2017.05.09】

  • 【策略梯度SeqGAN】《SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient》L Yu, W Zhang, J Wang, Y Yu [Shanghai Jiao Tong University & University College London] (2016)
    链接】【GitHub

【2017.05.10】

  • 《Improved Training of Wasserstein GANs》I Gulrajani, F Ahmed, M Arjovsky, V Dumoulin, A Courville [Montreal Institute for Learning Algorithms & Courant Institute of Mathematical Sciences] (2017)
    链接】【GitHub】【GitHub2
  • 《Geometric GAN》J H Lim, J C Ye [ETRI & KAIST] (2017)
    链接】【GitHub】
  • 【PyTorch实现的CycleGAN/SGAN跨域迁移(MNIST-to-SVHN & SVHN-to-MNIST)】’PyTorch Implementation of CycleGAN and SGAN for Domain Transfer (Minimal)’ by yunjey GitHub:
    【链接】【GitHub

1.2 神经网络

【2017.04.24】

  • 如何用PyTorch实现递归神经网络?
    链接】【GitHub】

【2017.04.25】

  • 一个基于TensorFlow的简单故事生成案例:带你了解LSTM
    链接】【GitHub】

【2017.05.07】

  • 深度学习10大框架对比分析
    链接】【GitHub】
  • 深度学习之CNN卷积神经网络
    链接】【GitHub】
  • 【Keras教程:Python深度学习】《Keras Tutorial: Deep Learning in Python》by Karlijn Willems
    链接】【GitHub】
  • TensorFlow 官方解读:如何在多系统和网络拓扑中构建高性能模型
    链接】【GitHub】
  • 从自编码器到生成对抗网络:一文纵览无监督学习研究现状
    链接】【GitHub】
  • 《Residual Attention Network for Image Classification》F Wang, M Jiang, C Qian, S Yang, C Li, H Zhang, X Wang, X Tang [SenseTime Group Limited & Tsinghua University & The Chinese University of Hong Kong] (2017)
    链接】【GitHub】
    -【基于OpenAI Gym/Tensorflow/Keras的增强学习实验平台】’OpenAI Lab - An experimentation system for Reinforcement Learning using OpenAI Gym, Tensorflow, and Keras.’ by Wah Loon Keng
    【链接】【GitHub
  • 【基于生成卷积网络的潜在指纹重建】《Generative Convolutional Networks for Latent Fingerprint Reconstruction》J Svoboda, F Monti, M M. Bronstein [USI Lugano] (2017)
    链接】【GitHub】
  • 【TensorFlow入门代码集锦】’tensorflow-resources - Curated Tensorflow code resources to help you get started’ by Skcript
    【链接】【GitHub
  • 入门级攻略:机器学习 VS. 深度学习
    链接】【GitHub】
  • 《Gabor Convolutional Networks》S Luan, B Zhang, C Chen, X Cao, J Han, J Liu [Beihang University & University of Central Florida Orlando & Northumbria University & Huawei Company] (2017)
    链接】【GitHub】
  • TensorFlow基准:图像分类模型在各大平台的测试研究
    链接】【GitHub】
  • 谷歌开源深度学习街景文字识别模型:让地图随世界实时更新
    链接】【GitHub】
  • 《Geometric deep learning: going beyond Euclidean data》M M. Bronstein, J Bruna, Y LeCun, A Szlam, P Vandergheynst [USI Lugano & NYU & Facebook AI Research] (2016)
    链接】【GitHub】
  • 【利用强化学习设计神经网络架构】《Designing Neural Network Architectures using Reinforcement Learning》B Baker, O Gupta, N Naik, R Raskar [MIT] (2016)
    链接】【GitHub
  • 【神经网络:三万英尺高空纵览入门】《Neural Networks : A 30,000 Feet View for Beginners | Learn OpenCV》by Satya Mallick
    链接】【GitHub】
  • Top100论文导读:深入理解卷积神经网络CNN(Part Ⅰ)
    链接】【GitHub】
  • Top100论文导读:深入理解卷积神经网络CNN(Part Ⅱ)
    链接】【GitHub】
    -【深度神经网络权值初始化的研究】《On weight initialization in deep neural networks》S K Kumar (2017)
    【链接】【GitHub

【2017.05.08】

  • 【提升结构化特征嵌入深度度量学习】《Deep Metric Learning via Lifted Structured Feature Embedding》H Oh Song, Y Xiang, S Jegelka, S Savarese (2016)
    链接】【GitHub

  • 【图的深度特征学习】《Deep Feature Learning for Graphs》R A. Rossi, R Zhou, N K. Ahmed [Palo Alto Research Center (Xerox
    PARC) & Intel Labs] (2017)
    链接】【GitHub】

  • 【用于性能分析、模型优化的神经网络生成器】’Perceptron - A flexible artificial neural network builder to analysis performance, and optimise the best model.’ by Caspar Wylie
    【链接】【GitHub
  • 【TensorFlow最佳实践之文件、文件夹与模型架构实用建议】《TensorFlow: A proposal of good practices for files, folders and models architecture》by Morgan
    链接】【GitHub】
  • 【带有快速局部滤波的图CNN】《Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering》M Defferrard, X Bresson, P Vandergheynst [EPFL] (2016)
    链接】【GitHub
  • 【(Tensorflow/TFLearn)RNN命名实体识别】“Named Entity Recognition using Recurrent Neural Networks in Tensorflow and TFLearn” by Dhwaj Raj
    【链接】【GitHub
  • 【深度学习的局限性】《Failures of Deep Learning》S Shalev-Shwartz, O Shamir, S Shammah [The Hebrew University & Weizmann Institute] (2017)
    链接】【GitHub】【video

  • 【基于矩阵乘法的并行多通道卷积】《Parallel Multi Channel Convolution using General Matrix Multiplication》A Vasudevan, A Anderson, D Gregg [Trinity College Dublin] (2017)
    链接】【GitHub】

  • 【在手机上进行深度学习训练】《Migrate Deep Learning Training onto Mobile Devices!》by Saman BigManborn
    链接】【GitHub】
  • 【TensorFlow实现的RNN(LSTM)序列预测】’tensorflow-lstm-regression - Sequence prediction using recurrent neural networks(LSTM) with TensorFlow’ by mouradmourafiq
    【链接】【GitHub
  • 【TensorFlow 1.1.0发布】”TensorFlow 1.1.0 Released”
    【链接】【GitHub
  • 【CNN到图结构数据的推广】《A Generalization of Convolutional Neural Networks to Graph-Structured Data》Y Hechtlinger, P Chakravarti, J Qin [CMU] (2017)
    链接】【GitHub

  • Momenta研发总监任少卿:From Faster R-CNN to Mask R-CNN
    链接】【GitHub】

  • 《Deep Multitask Learning for Semantic Dependency Parsing》H Peng, S Thomson, N A. Smith [CMU] (2017)
    链接】【GitHub

  • 【利用整流单元稀疏性加快卷积神经网络】《Speeding up Convolutional Neural Networks By Exploiting the Sparsity of Rectifier Units》S Shi, X Chu [Hong Kong Baptist University] (2017)
    链接】【GitHub】

  • 【深度学习之CNN卷积神经网络】《Deep Learning #2: Convolutional Neural Networks》by Rutger Ruizendaal
    链接】【GitHub】
  • 【PyTorch试炼场:提供各主流预训练模型】’pytorch-playground - Base pretrained model and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)’ by Aaron Chen
    【链接】【GitHub
  • 从自编码器到生成对抗网络:一文纵览无监督学习研究现状
    链接】【GitHub】

【2017.05.09】

  • Learning Deep Learning with Keras
    链接】【GitHub】
  • 【TensorFlow生成模型库】’A Library for Generative Models’
    【链接】【GitHub
  • 【深度学习的过去、现在和未来】《Deep Learning – Past, Present, and Future》by Henry H. Eckerson
    链接】【GitHub】
  • 正在涌现的新型神经网络模型:优于生成对抗网络
    链接】【GitHub】
  • 【贝叶斯深度学习文献列表】’A curated list of resources dedicated to bayesian deep learning’ by Rabindra Nath Nandi
    【链接】【GitHub
  • 【面向推荐系统的深度学习文献列表】’Deep-Learning-for-Recommendation-Systems - Deep Learning based articles , paper and repositories for Recommender Systems’ by Rabindra Nath Nandi
    【链接】【GitHub

【2017.05.10】

  • 【深度学习职位面试经验分享】《My deep learning job interview experience sharing》by Justin Ho
    链接】【GitHub】
  • 《Convolutional Sequence to Sequence Learning》J Gehring, M Auli, D Grangier, D Yarats, Y N. Dauphin [Facebook AI Research] (2017)
    链接】【GitHub】
  • 【VGG19的TensorFlow实现/详解】’VGG19_with_tensorflow - An easy implement of VGG19 with tensorflow, which has a detailed explanation.’ by Jipeng Huang
    【链接】【GitHub
  • 【Keras实现的深度聚类】“Keras implementation of Deep Clustering paper” by Eduardo Silva
    【链接】【GitHub

1.3 机器学习

【2017.05.07】

  • 【无监督学习纵览】《Navigating the Unsupervised Learning Landscape》by Eugenio Culurciello
    链接】【GitHub】
  • 【(Python)机器学习导论课程资料】’Materials for the “Introduction to Machine Learning” class’ by Andreas Mueller
    【链接】【GitHub
  • 【Newton ADMM快速准平滑牛顿法】’A Newton ADMM based solver for Cone programming.’
    【链接】【GitHub
  • 【超大规模机器学习工具集MaTEx】’Machine Learning Toolkit for Extreme Scale (MaTEx) - a collection of high performance parallel machine learning and data mining (MLDM) algorithms, targeted for desktops, supercomputers and cloud computing systems’
    【链接】【GitHub
  • 关于迁移学习的一些资料
    【链接】【GitHub
  • 《Clustering with Adaptive Structure Learning: A Kernel Approach》Z Kang, C Peng, Q Cheng [Southern Illinois University] (2017)
    链接】【GitHub】
  • 【(R)稀疏贝叶斯网络学习】’sparsebn - Software for learning sparse Bayesian networks’ by Bryon Aragam
    【链接】【GitHub
  • 【Node.js机器学习/自然语言处理/情感分析工具包】’salient - Machine Learning, Natural Language Processing and Sentiment Analysis Toolkit for Node.js’ by Thomas Holloway
    【链接】【GitHub
  • Explaining the Success of AdaBoost and Random Forests as Interpolating Classifiers
    链接】【GitHub】
  • 机器学习中容易犯下的错
    链接】【GitHub】

【2017.05.08】

  • 【(C/C++ and MATLAB/Octave)互信息函数工具箱】’MIToolbox - Mutual Information functions for C and MATLAB’ by Adam Pocock
    【链接】【GitHub
  • 【Criteo 1TB数据集上多机器学习算法Benchmark】’Benchmark of different ML algorithms on Criteo 1TB dataset’ by Rambler Digital Solutions
    【链接】【GitHub
  • 机器学习十大常用算法
    链接】【GitHub】
  • 【加速随机梯度下降】《Accelerating Stochastic Gradient Descent》P Jain, S M. Kakade, R Kidambi, P Netrapalli, A Sidford [Microsoft Research & University of Washington & Stanford University] (2017)
    链接】【GitHub】
  • 【(C++)大规模稀疏矩阵分解包】“LIBMF - library for large-scale sparse matrix factorization” by cjlin1
    【链接】【GitHub
  • 【(C/Python/Matlab)求解大规模正则线性分类与回归的简单包】“LIBLINEAR - simple package for solving large-scale regularized linear classification and regression” by cjlin1
    【链接】【GitHub
  • 【批量归一化(Batch Norm)概述】《Appendix: A Batch Norm Overview》by alexirpan
    链接】【GitHub】

【2017.05.09】

  • 谱聚类
    链接】【GitHub】

【2017.05.10】

  • 【学习非极大值抑制】《Learning non-maximum suppression》J Hosang, R Benenson, B Schiele [Max Planck Institut für Informatik] (2017)
    链接】【GitHub】
  • 【(Python)机器学习工作流框架】’AlphaPy - Machine Learning Pipeline for Python’ by ScottFree Analytics
    【链接】【GitHub
  • 【如何解释机器学习模型和结果】《Ideas on interpreting machine learning | O’Reilly Media》by Patrick HallWen Phan, SriSatish Ambati
    链接】【GitHub】

2、计算机视觉

【2017.04.21】

  • OpenCV/Python/dlib人脸关键点实时标定
    paper】【GitHub】

【2017.04.22】

  • 【高效的卷积神经网络在手机中的应用】MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
    paper】【GitHub】
  • 【生成式人脸补全】《Generative Face Completion》Y Li, S Liu, J Yang, M-H Yang [Univerisity of California, Merced & Adobe Research] (2017)
    【paper】【GitHub
  • 《Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art》J Janai, F Güney, A Behl, A Geiger [Max Planck Institute for Intelligent Systems & ETH Zurich] (2017)
    paper】【GitHub】
  • 《Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking》L Leal-Taixé, A Milan, K Schindler, D Cremers, I Reid, S Roth [Technical University Munich & University of Adelaide & ETH Zurich & TU Darmstadt] (2017)《译:多目标追踪的现状分析》
    paper】【GitHub】
  • 《CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction》K Tateno, F Tombari, I Laina, N Navab [CAMP - TU Munich] (2017)
    paper】【GitHub】
  • 《Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields》Z Cao, T Simon, S Wei, Y Sheikh [CMU] (2016)《译:基于PAF的实时二维姿态估计》
    paper】【GitHub
  • 《Virtual to Real Reinforcement Learning for Autonomous Driving》Y You, X Pan, Z Wang, C Lu [Shanghai Jiao Tong University & UC Berkeley & Tsinghua University] (2017)
    paper】【GitHub】
  • 《Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark》T Hackel, N Savinov, L Ladicky, J D. Wegner, K Schindler, M Pollefeys [ETH Zurich] (2017)
    paper】【GitHub
  • 《Learning Video Object Segmentation with Visual Memory》P Tokmakov, K Alahari, C Schmid [Inria] (2017)
    paper】【GitHub】

【2017.04.23】

  • 《A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN》by Dhruv Parthasarathy
    paper】【GitHub】
  • 《Stacked Hourglass Networks for Human Pose Estimation》A Newell, K Yang, J Deng [University of Michigan] (2016)
    paper】【GitHub】
  • 自动驾驶计算机视觉研究综述:难题、数据集与前沿成果(附67页论文下载)
    paper】【GitHub】
  • 谷歌推出最新“手机版”视觉应用的卷积神经网络—MobileNets
    paper】【GitHub】
  • 《Deep Learning for Photo Editing》by Malte Baumann
    paper】【GitHub】

【2017.04.24】

  • TensorFlow Implementation of conditional variational auto-encoder (CVAE) for MNIST by hwalsuklee
    【paper】【GitHub

【2017.04.26】

  • 【单目视频深度帧间运动估计无监督学习框架】’SfMLearner - An unsupervised learning framework for depth and ego-motion estimation from monocular videos’ by T Zhou
    paper】【GitHub

  • “U-Nets(Caffe)”
    paper】【GitHub】

  • 《U-Net: Convolutional Networks for Biomedical Image Segmentation》(2015)
    paper】【GitHub】
  • 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
    paper】【GitHub】

【2017.05.07】

  • 【(C++/Matlab)视频/图片序列人脸标定】’Find Face Landmarks - C++ \ Matlab library for finding face landmarks and bounding boxes in video\image sequences.’ by Yuval Nirkin
    【paper】【GitHub
  • 【(Keras)UNET图像分割】’ZF_UNET_224 Pretrained Model - Modification of convolutional neural net “UNET” for image segmentation in Keras framework’ by ZFTurbo
    【paper】【GitHub
  • 【复杂条件下的深度人脸分割】”Deep face segmentation in extremely hard conditions” by Yuval Nirkin
    paper】【GitHub

  • 【基于单目RGB图像的实时3D人体姿态估计】《VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera》D Mehta, S Sridhar, O Sotnychenko… [Max Planck Institute for Informatics & Universidad Rey Juan Carlos] (2017)
    paper】【paper2】【GitHub】

  • 【衣服检测与识别】《DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations》Z Liu, P Luo, S Qiu, X Wang, X Tang (CVPR 2016)
    paper
    paper2】【GitHub

  • SLAM 学习与开发经验分享
    【paper】【GitHub

  • 【大规模街道级图片(分割)数据集】《Releasing the World’s Largest Street-level Imagery Dataset for Teaching Machines to See》by Peter Kontschieder
    paper】【GitHub】【dataset

  • 【基于深度增强学习的交叉路口车辆自动导航】《Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning》D Isele, A Cosgun, K Subramanian, K Fujimura [University of Pennsylvania & Honda Research Institute & Georgia Institute of Technology] (2017)
    paper】【GitHub】

  • 十分钟看懂图像语义分割技术
    paper】【GitHub】
  • 【(C++)实时多人关键点检测】’OpenPose: A Real-Time Multi-Person Keypoint Detection And Multi-Threading C++ Library’
    【paper】【GitHub
  • 计算机视觉、机器学习相关领域论文和源代码大集合
    paper】【GitHub】
  • 【(Tensorflow)RPN+人体检测】’RPNplus - RPN+(Tensorflow) for people detection’ by Shiyu Huang
    【paper】【GitHub
  • 【(C++/OpenCV3)实时可变人脸追踪】’Real time deformable face tracking in C++ with OpenCV 3.’ by Kyle McDonald
    【paper】【GitHub
  • 【图片快速标记】《How to Label Images Quickly 》by Pete Warden
    paper】【paper2】【GitHub】

  • 【基于深度图像类比的视觉要素迁移】《Visual Attribute Transfer through Deep Image Analogy》J Liao, Y Yao, L Yuan, G Hua, S B Kang [Microsoft Research & Shanghai Jiao Tong University] (2017)
    paper】【GitHub】

  • 【基于深度学习的质谱成像中的肿瘤分类】《Deep Learning for Tumor Classification in Imaging Mass Spectrometry》J Behrmann, C Etmann, T Boskamp, R Casadonte, J Kriegsmann, P Maass [University of Bremen & Proteopath GmbH] (2017)
    paper】【link2】【GitHub

  • 【Andorid手机上基于TensorFlow的人体行为识别】《Deploying Tensorflow model on Andorid device for Human Activity Recognition》by Aaqib Saeed
    paper】【paper2】【GitHub

  • 【TensorFlow图像自动描述】《Caption this, with TensorFlow | O’Reilly Media》by Raul Puri, Daniel Ricciardelli
    paper】【paper2】【GitHub
  • 【基于CNN (InceptionV1) + STFT的Kaggle鲸鱼检测竞赛方案】’CNN (InceptionV1) + STFT based Whale Detection Algorithm - A whale detector design for the Kaggle whale-detector challenge!’ by Tarin Ziyaee
    【paper】【GitHub
  • 【TensorFlow实现的摄像头pix2pix图图转换】’webcam-pix2pix-Tensorflow - Source code and pretrained model for webcam pix2pix’ by Memo Akten
    【paper】【GitHub
  • 【图像分类的大规模进化】《Large-Scale Evolution of Image Classifiers》E Real, S Moore, A Selle, S Saxena, Y L Suematsu, Q Le, A Kurakin [Google Brain & Google Research] (2017)
    paper】【paper2】【GitHub】

【2017.05.08】

  • 人脸检测与识别的趋势和分析
    paper】【GitHub】
  • 【全局/局部一致图像补全】《Globally and Locally Consistent Image Completion》S Iizuka, E Simo-Serra, H Ishikawa (2017)
    paper】【GitHub】
  • 【基于CNN的面部表情识别】《Convolutional Neural Networks for Facial Expression Recognition》S Alizadeh, A Fazel [Stanford University] (2017)
    paper】【GitHub】
  • 计算机视觉识别简史:从 AlexNet、ResNet 到 Mask RCNN
    paper】【GitHub】
  • 【脸部识别与聚类】《Face Identification and Clustering》A Dhingra [The State University of New Jersey] (2017)
    paper】【GitHub】
  • 【(TensorFlow)通用U-Net图像分割】’Tensorflow Unet - Generic U-Net Tensorflow implementation for image segmentation’ by Joel Akeret
    【paper】【GitHub
  • 【深度学习介绍之文本图像生成】《How to Convert Text to Images - Intro to Deep Learning #16 - YouTube》by Siraj Raval
    paper】【GitHub】
  • 【一个深度神经网络如何对自动驾驶做端到端的训练】《Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car》M Bojarski, P Yeres, A Choromanska, K Choromanski, B Firner, L Jackel, U Muller [NVIDIA Corporation & New York University & Google Research] (2017)
    paper】【GitHub】
  • 【基于深度卷积网络的动态场景关节语义与运动分割】《Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks》N Haque, N D Reddy, K. M Krishna [International Institute of Information Technology & Max Planck Institute For Intelligent Systems] (2017)
    paper】【GitHub】
  • 【高分辨率图像的实时语义分割】《ICNet for Real-Time Semantic Segmentation on High-Resolution Images》H Zhao, X Qi, X Shen, J Shi, J Jia [The Chinese University of Hong Kong & SenseTime Group Limited] (2017)
    paper】【GitHub】【GitHub2】【video
  • 【深度学习应用到语义分割的综述】《A Review on Deep Learning Techniques Applied to Semantic Segmentation》A Garcia-Garcia, S Orts-Escolano, S Oprea, V Villena-Martinez, J Garcia-Rodriguez [University of Alicante] (2017)
    paper】【GitHub】
  • 【医学图像的深度迁移学习的原理】《Understanding the Mechanisms of Deep Transfer Learning for Medical Images》H Ravishankar, P Sudhakar, R Venkataramani, S Thiruvenkadam, P Annangi, N Babu, V Vaidya [GE Global Research] (2017)
    paper】【GitHub】
  • 【(Torch)基于循环一致对抗网络的非配对图到图翻译】
    【paper】【GitHub
  • 【深度网络光流估计的演化】《FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks》E Ilg, N Mayer, T Saikia, M Keuper, A Dosovitskiy, T Brox [University of Freiburg] (2016)
    paper】【GitHub】【video

  • 【基于p-RNN的目标实例标注】《Annotating Object Instances with a Polygon-RNN》L Castrejon, K Kundu, R Urtasun, S Fidler [University of Toronto] (2017)
    paper】【GitHub】

  • 《Dataset Augmentation for Pose and Lighting Invariant Face Recognition》D Crispell, O Biris, N Crosswhite, J Byrne, J L. Mundy [Vision Systems, Inc & Systems and Technology Research] (2017)
    paper】【GitHub】
  • 【人脸的分割、交换与感知】《On Face Segmentation, Face Swapping, and Face Perception》Y Nirkin, I Masi, A T Tran, T Hassner, G Medioni [The Open University of Israel & USC] (2017)
    paper】【GitHub】
  • 【面向视频运动估计的几何感知神经网络SfM-Net】《SfM-Net: Learning of Structure and Motion from Video》S Vijayanarasimhan, S Ricco, C Schmid, R Sukthankar, K Fragkiadaki [Google & Indri & CMU] (2017)
    paper】【GitHub】
  • 【基于深度自学习的弱监督目标定位】《Deep Self-Taught Learning for Weakly Supervised Object Localization》Z Jie, Y Wei, X Jin, J Feng, W Liu [Tencent AI Lab & National University of Singapore] (2017)
    paper】【GitHub】
  • 【单个图像的手部关键点检测】《Hand Keypoint Detection in Single Images using Multiview Bootstrapping》T Simon, H Joo, I Matthews, Y Sheikh [CMU] (2017)
    paper】【GitHub】
  • 《Hierarchical 3D fully convolutional networks for multi-organ segmentation》H R. Roth, H Oda, Y Hayashi, M Oda, N Shimizu, M Fujiwara, K Misawa, K Mori [Nagoya University & Nagoya University Graduate School of Medicine & Aichi Cancer Center] (2017)
    paper】【GitHub】
  • 《Towards Large-Pose Face Frontalization in the Wild》X Yin, X Yu, K Sohn, X Liu, M Chandraker [Michigan State University & NEC Laboratories America & University of California, San Diego] (2017)
    paper】【paper2】【GitHub】

  • 【通过观察目标运动迁移学习特征】《Learning Features by Watching Objects Move》D Pathak, R Girshick, P Dollár, T Darrell, B Hariharan [Facebook AI Research & UC Berkeley] (2016)
    paper】【GitHub

  • 【面向深度学习训练的视频标记工具】’BeaverDam - Video annotation tool for deep learning training labels’ by Anting Shen
    【paper】【GitHub

  • 【生成对抗网络(GAN)图片编辑】《Photo Editing with Generative Adversarial Networks | Parallel Forall》by Greg Heinrich
    paper】【paper2】【GitHub

  • 解读Keras在ImageNet中的应用:详解5种主要的图像识别模型
    paper】【GitHub】

  • 《Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation》Y Chen, C Shen, X Wei, L Liu, J Yang [Nanjing University of Science and Technology & The University of Adelaide & Nanjing University] (2017)
    paper】【GitHub】
  • 【结构感知卷积网络的人体姿态估计】《Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation》Y Chen, C Shen, X Wei, L Liu, J Yang [Nanjing University of Science and Technology & The University of Adelaide & Nanjing University] (2017)
    paper】【GitHub】
  • 【基于神经网络的鲁棒多视角行人跟踪】《Robust Multi-view Pedestrian Tracking Using Neural Networks》M Z Alom, T M. Taha [University of Dayton] (2017)
    paper】【GitHub】
  • 【视频密集事件描述】”Dense-Captioning Events in Videos”
    paper】【GitHub】【data

  • 【受Siraj Raval深度学习视频启发的每周深度学习实践挑战】’Deep-Learning Challenges - Codes for weekly challenges on Deep Learning by Siraj’ by Batchu Venkat Vishal
    paper】【GitHub】

  • 《SLAM with Objects using a Nonparametric Pose Graph》B Mu, S Liu, L Paull, J Leonard, J How [MIT] (2017)
    paper】【GitHub

  • 【医学图像分割中迭代估计的归一化输入】《Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation》M Drozdzal, G Chartrand, E Vorontsov, L D Jorio, A Tang, A Romero, Y Bengio, C Pal, S Kadoury [Universite de Montreal & Imagia Inc] (2017)
    paper】【GitHub】

  • 《An Analysis of Action Recognition Datasets for Language and Vision Tasks》S Gella, F Keller [University of Edinburgh] (2017)
    paper】【GitHub】

【2017.05.09】

  • Tensorflow实现卷积神经网络,用于人脸关键点识别
    paper】【GitHub】
  • 【FRCN(faster-rcnn)文字检测】’Text-Detection-using-py-faster-rcnn-framework’ by jugg1024
    【paper】【GitHub
  • 【手机单目视觉状态估计器】’VINS-Mobile - Monocular Visual-Inertial State Estimator on Mobile Phones’ by HKUST Aerial Robotics Group
    paper】【GitHub

  • 【R-FCN目标检测】R-FCN: Object Detection via Region-based Fully Convolutional Networks
    paper】【GitHub

  • 行人检测、跟踪与检索领域年度进展报告
    paper】【GitHub】

  • 【(TensorFlow)点云(Point Cloud)分类、分割、场景语义理解统一框架PointNet】’PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation’
    paper】【paper2】【GitHub】【GitHub2
  • 【深度视频去模糊】《Deep Video Deblurring》by Shuochen Su(2016)
    paper】【paper2】【GitHub】【video
  • 【中国的Infervision及其肺癌诊断AI工具】《Chinese startup Infervision emerges from stealth with an AI tool for diagnosing lung cancer | TechCrunch》by Jonathan Shieber
    paper】【paper2】【GitHub】

  • 【基于医院大量胸部x射线数据库的弱监督分类和常见胸部疾病定位的研究】《ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases》X Wang, Y Peng, L Lu, Z Lu… [National Institutes of Health] (2017)
    paper】【paper2】【GitHub】

  • 目标跟踪方法的发展概述
    paper】【GitHub】

  • 【(Caffe)实时交互式图片自动着色】《Real-Time User-Guided Image Colorization with Learned Deep Priors》[UC Berkeley] (2017)
    paper】【paper2】【GitHub】【video
  • 相术的新衣】《Physiognomy’s New Clothes》by Blaise Aguera y Arcas
    paper】【GitHub】

【2017.05.10】

  • 快速生成人脸模型
    paper】【paper2】【GitHub(预计八月开源)】
  • VALSE2017系列之二: 边缘检测领域年度进展报告
    paper】【GitHub】
  • 【(GTC2017)Stanford发布0.5PB大规模放射医疗图像ImageNet数据集】“Stanford gave the world ImageNet. Now it’s giving the world Medical ImageNet—a 0.5PB dataset for diagnostic radiology” via:James Wang
    paper】【GitHub】
  • 【医疗图像深度学习】《Medical Image Analysis with Deep Learning》by Taposh Dutta-Roy
    Part1
    Part2
    Part3
  • 【激光雷达(LIDAR):自驾车关键传感器】《An Introduction to LIDAR: The Key Self-Driving Car Sensor》by Oliver Cameron
    paper】【GitHub】
  • 【根据目标脸生成带语音的视频】《You said that?》J S Chung, A Jamaludin, A Zisserman [University of Oxford] (2017)
    paper】【GitHub】
  • 【用于图像生成和数据增强的生成协作网】《Generative Cooperative Net for Image Generation and Data Augmentation》Q Xu, Z Qin, T Wan [Beihang University & Alibaba Group] (2017)
    paper】【GitHub】
  • 【COCO像素级标注数据集】’The official homepage of the COCO-Stuff dataset.’
    【paper】【GitHub
  • 《COCO-Stuff: Thing and Stuff Classes in Context》 (2017) 【paper】【GitHub】
  • 【LinkNet:基于编码器表示的高效语义分割】《(LinkNet)Feature Forwarding: Exploiting Encoder Representations for Efficient Semantic Segmentation》A Chaurasia, E Culurciello
    paper】【GitHub】【GitHub2

3、自然语言处理

【2017.04.22】

  • 《Semantic Instance Segmentation via Deep Metric Learning》A Fathi, Z Wojna, V Rathod, P Wang, H O Song, S Guadarrama, K P. Murphy [Google Inc & UCLA] (2017)
    paper】【GitHub】

【2017.04.26】

  • 【对话语料集】’chat corpus collection from various open sources’ by Marsan-Ma
    【paper】【GitHub

【2017.05.07】

  • 【从文本中提取特征的神经网络技术综述】《A Survey of Neural Network Techniques for Feature Extraction from Text》V John [University of Waterloo] (2017)
  • 基於向量匹配的情境式聊天機器人’ by Justin Yang
    【paper】【GitHub
  • 【PyTorch实践:序列到序列Attention法-英翻译】《Practical PyTorch: Translation with a Sequence to Sequence Network and Attention》by Sean Robertson
    【paper】【GitHub
  • 【PyTorch实践:探索GloVe词向量】《Practical PyTorch: Exploring Word Vectors with GloVe》by Sean Robertson
    【paper】【GitHub
  • 【自然语言生成(NLG)系统评价指标】《How to do an NLG Evaluation: Metrics》by Ehud Reiter
    paper】【paper2】【GitHub】
  • 【看似靠谱的文本分类对抗样本】’textfool - Plausible looking adversarial examples for text classification’ by Bogdan Kulynych >【paper】【GitHub
  • 【基于bidirectional GRU-CRF的联合中文分词与词性标注】’A Joint Chinese segmentation and POS tagger based on bidirectional GRU-CRF’ by yanshao9798
    【paper】【GitHub
  • 【自然语言处理(NLP)入门指南】《How to get started in NLP》by Melanie Tosik
    paper】【GitHub】

【2017.05.08】

  • 【(TensorFlow)面向文本相似度检测的Deep LSTM siamese网络】’Deep LSTM siamese network for text similarity - Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character embeddings’ by Dhwaj Raj
    【paper】【GitHub
  • 【Keras/TensorFlow语种检测】《Deep Learning: Language identification using Keras & TensorFlow》by Lucas KM
    paper】【GitHub
    -【(C++)神经网络语种检测工具】“Compact Language Detector v3 (CLD3) - neural network model for language identification” by Google
    【paper】【GitHub
  • 【用于文本分类的端到端多视图网络】《End-to-End Multi-View Networks for Text Classification》H Guo, C Cherry, J Su [National Research Council Canada] (2017)
    paper】【GitHub】
  • 【理解非结构化文本数据】《Making Sense of Unstructured Text Data》L Li, W M. Campbell, C Dagli, J P. Campbell [MIT Lincoln Laboratory] (2017)
    paper】【GitHub】
  • 【非本族语者英语写作风格检测】《Detecting English Writing Styles For Non Native Speakers》Y Chen, R Al-Rfou’, Y Choi [Stony Brook University] (2017)
    paper】【GitHub】

【2017.05.10】

  • Facebook提出全新CNN机器翻译:准确度超越谷歌而且还快九倍(已开源)
    paper1】【paper2】【GitHub

4、应用案例

【2017.04.21】

  • 深度学习入门实战(一)-像Prisma一样算法生成梵高风格画像
    paper】【GitHub】

【2017.04.22】

  • 我们教电脑识别视频字幕
    paper】【GitHub】

【2017.04.24】

  • 《Data Sciencing Motorcycles: Lean Assist》by Josh Peng
    paper】【GitHub

【2017.04.26】

  • 【PhotoScan新增的去除翻拍反光功能】《PhotoScan: Taking Glare-Free Pictures of Pictures | Google Research Blog》by Ce Liu, Michael Rubinstein, Mike Krainin, Bill Freeman
    paper】【GitHub】

【2017.05.08】

  • 【假新闻的实时检测】《How to Detect Fake News in Real-Time 》by Krishna Bharat
    paper】【GitHub】

5、综合

5.1 教程

【2017.04.21】

  • 30 Free Courses: Neural Networks, Machine Learning, Algorithms, AI
    paper】【GitHub】

【2017.04.22】

  • 【Deep Learning】
    英文原文:【link
    中文译文:【link
    中文译文说明:【link

【2017.04.23】

  • 机器学习(Machine Learning)&深度学习(Deep Learning)资料(Chapter 1)
    【paper】【GitHub

【2017.05.07】

  • 【台大李宏毅中文深度学习课程(2017)】”NTUEE Machine Learning and having it Deep and Structured(MLDS) (2017)”
    【paper】【GitHub】【video
  • TensorFlow教程
    【paper】【GitHub

【2017.05.08】

  • 【Keras教程:Python深度学习】《Keras Tutorial: Deep Learning in Python》by Karlijn Willems
    paper】【GitHub】

【2017.05.09】

  • 【用Anaconda玩转深度学习】《Deep Learning with Anaconda(AnacondaCON 2017) - YouTube》by Stan Seibert & Matt Rocklin
    【paper】【GitHub】【video

5.2 其它

【2017.04.23】

  • 哥伦比亚大学与Adobe提出新方法,可将随机梯度下降用作近似贝叶斯推理
    paper】【GitHub】
  • 英特尔深度学习产品综述:如何占领人工智能市场
    paper】【GitHub】

【2017.04.24】

  • 28款GitHub最流行的开源机器学习项目:TensorFlow排榜首
    paper】【GitHub】

【2017.04.26】

  • 英国皇家学会百页报告:机器学习的力量与希望(豪华阵容参与完成)
    paper】【GitHub】
  • 深度学习在推荐算法上的应用进展
    paper】【GitHub】
  • 周志华教授gcForest(多粒度级联森林)算法预测股指期货涨跌
    paper】【GitHub】

【2017.05.07】

  • 市值250亿的特征向量——谷歌背后的线性代数
    paper】【GitHub】
  • 【可重现/易分享数据科学项目框架】’DVC - Data Version Control: Make your data science projects reproducible and shareable
    【paper】【GitHub
  • 《Fast k-means based on KNN Graph》C Deng, W Zhao [Xiamen University] (2017)
    paper】【GitHub】
  • 【信息检索人工神经网络模型】《Neural Models for Information Retrieval》B Mitra, N Craswell [Microsoft] (2017)
    paper】【GitHub】
  • 地平线机器人杨铭:深度神经网络在图像识别应用中的演化
    paper】【GitHub】
  • 【(Python)Facebook的开源AI对话研究框架】’ParlAI - A framework for training and evaluating AI models on a variety of openly available dialog datasets.’
    【paper】【GitHub
  • 【(Python)深度神经网络多标签文本分类框架】’magpie - Deep neural network framework for multi-label text classification’ by inspirehep
    【paper】【GitHub
  • 【(300万)Instacart在线杂货购物数据集】《3 Million Instacart Orders, Open Sourced》by Jeremy Stanley
    paper】【GitHub】
  • 【基于语言/网络结构的推荐系统GraphNet】《GraphNet: Recommendation system based on language and network structure》R Ying, Y Li, X Li [Stanford University] (2017)
    paper】【GitHub】

【2017.05.08】

  • 【将Python 3.x代码转换成Python2.x代码的Python-Python编译器】’Py-backwards - Python to python compiler that allows you to use Python 3.6 features in older versions.’ by Vladimir Iakovlev
    【paper】【GitHub

【2017.05.09】

  • 【Xgboost新增GPU加速建树算法】”Xgboost GPU - CUDA Accelerated Tree Construction Algorithm”
    【paper】【GitHub
  • 【独立开发者赚钱资料集锦】’awesome-indie - Resources for independent developers to make money’ by Joan Boixadós
    【paper】【GitHub
  • 【基于MAPD/Anaconda/H2O的GPU数据分析框架】’GPU Data Frame with a corresponding Python API’
    【paper】【GitHub
  • 从文本到视觉:各领域最前沿的论文集合
    paper】【GitHub】

【2017.05.10】

  • 【(C++)信息检索框架库Trinity】’Trinity IR Infrastructure’ by Phaistos Networks GitHub:
    【paper】【GitHub

参考

阅读更多
个人分类: 机器学习
上一篇Ubuntu14.04重启搜狗输入法
下一篇详细解释CNN卷积神经网络各层的参数和链接个数的计算
想对作者说点什么? 我来说一句

没有更多推荐了,返回首页

关闭
关闭
关闭