歡迎光臨
每天分享高質量文章

純乾貨18 – 2016-2017深度學習-最新-必讀-經典論文

    收集主要整理了2016-2017年深度學習NLP、圖像及語音等領域應用最前沿、最經典的論文。文章主要內容整理自網絡。

目錄:

1 代碼方面

    1.1   代碼生成

    1.2   惡意軟體檢測/安全

2 NLP領域

    2.1   摘要生成

    2.2   Taskbots

    2.3   分類

    2.4   問答系統

    2.5   情感分析

    2.6   機器翻譯

    2.7   聊天機器人

    2.8   推理

3 計算及視覺方面

    3.1   游戲應用

    3.2   風格遷移

    3.3   物體跟蹤

    3.4   視覺問答

    3.5   圖像分割

    3.6   文本識別

    3.7   大腦計算機交互

    3.8   自動駕駛

    3.9   物件識別

    3.10   標識識別

    3.11   高清晰度處理

    3.12   姿態估計

    3.13   圖像標記

    3.14   圖像壓縮

    3.15   圖像合成

    3.16   人臉識別

4 語音方面

    4.1   語音合成

5 其他

    5.1   未分類

    5.2   正則

    5.3   神經網絡壓縮

    5.4   優化器

1 代碼方面


    1.1   代碼生成

    DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning 25 apr 2017

    A Syntactic Neural Model for General-Purpose Code Generation 6 apr 2017

    RobustFill: Neural Program Learning under Noisy I/O 21 mar 2017

    DeepFix: Fixing Common C Language Errors by Deep Learning 12 feb 2017

DeepCoder: Learning to Write Programs 7 nov 2016

    Neuro-Symbolic Program Synthesis 6 nov 2016

    Deep API Learning 27 may 2016


    1.2   惡意軟體檢測/安全

    PassGAN: A Deep Learning Approach for Password Guessing 1 sep 2017

Deep Android Malware Detection 22 mar 2016 paper

    Droid-Sec: Deep Learning in Android Malware Detection 17 aug 2014 paper

2   NLP領域


    2.1   摘要生成

    A Deep Reinforced Model for Abstractive Summarization 11 may 2017

    Get To The Point: Summarization with Pointer-Generator Networks 14 apr 2017

    SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents 14 nov 2016


    2.2   Taskbots

    Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning 10 apr 2017 arxiv

    End-to-End Task-Completion Neural Dialogue Systems 3 mar 2017 arxiv


    2.3   分類

    A Large Self-Annotated Corpus for Sarcasm 19 apr 2017

    ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge 11 apr 2017

    Bilateral Multi-Perspective Matching for Natural Language Sentences 13 feb 2017

    FastText.zip: Compressing text classification models 12 dec 2016

    ConceptNet 5.5: An Open Multilingual Graph of General Knowledge 12 dec 2016

    A Simple but Tough-to-Beat Baseline for Sentence Embeddings 4 nov 2016 paper

Enriching Word Vectors with Subword Information 15 jul 2016

    From Word Embeddings To Document Distances 6 jul 2016 paper

    Bag of Tricks for Efficient Text Classification 6 jul 2016

    Character-level Convolutional Networks for Text Classification 4 sep 2015

    GloVe: Global Vectors for Word Representation 25 may 2015 paper

    Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks 28 feb 2015

    Distributed Representations of Sentences and Documents 16 may 2014

    Efficient Estimation of Word Representations in Vector Space 16 jan 2013

    SimHash: Hash-based Similarity Detection 13 dec 2007


    2.4   問答系統

    IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models 30 may 2017 arxiv github state-of-the-art


    2.5   情感分析

    Rationalizing Neural Predictions 13 jun 2016

    Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank 18 okt 2013


    2.6   機器翻譯

    Attention Is All You Need 12 jun 2017 arxiv  state-of-the-art

    Convolutional Sequence to Sequence Learning 8 may 2017 arxiv github state-of-the-art

    Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation 14 nov 2016

    A Convolutional Encoder Model for Neural Machine Translation 7 nov 2016

    Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 26 sep 2016

    Neural Machine Translation by Jointly Learning to Align and Translate 1 sep 2014


    2.7   聊天機器人

    A Deep Reinforcement Learning Chatbot 7 sep 2017

    A Neural Conversational Model 19 jun 2015 arxiv


    2.8   推理

    Tracking the World State with Recurrent Entity Networks 12 dec 2016

3 計算及視覺方面

 

    3.1   游戲應用

    Phase-Functioned Neural Networks for Character Control 1 may 2017

Equivalence Between Policy Gradients and     Soft Q-Learning 21 apr 2017 arxiv  deep-q-learning Beating Atari with Natural Language Guided Reinforcement Learning 18 apr 2017 arxiv  deep-q-learning

    Learning from Demonstrations for Real World Reinforcement Learning 12 apr 2017 arxiv  deep-q-learning

    FeUdal Networks for Hierarchical Reinforcement Learning 3 mar 2017 arxiv  deep-q-learning

    Overcoming catastrophic forgetting in neural networks 2 dec 2016 arxiv  deep-q-learning

    Playing Doom with SLAM-Augmented Deep Reinforcement Learning 1 dec 2016

Playing FPS Games with Deep Reinforcement Learning 18 sep 2016

    DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess 16 aug 2016

    Generative Adversarial Imitation Learning 10 jun 2016

    Dueling Network Architectures for Deep Reinforcement Learning 20 nov 2015 arxiv  deep-q-learning

    Prioritized Experience Replay 18 nov 2015

    Human-level control through deep reinforcement learning 26 feb 2015 paper  deep-q-learning

    Playing Atari with Deep Reinforcement Learning 19 dec 2013 arxiv  deep-q-learning

 

    3.2   風格遷移

    Deep Photo Style Transfer 22 mar 2017

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization 20 mar 2017 arxiv

    A Learned Representation For Artistic Style 24 okt 2016

    Instance Normalization: The Missing Ingredient for Fast Stylization 27 jul 2016

    Perceptual Losses for Real-Time Style Transfer and Super-Resolution 27 mar 2016 arxiv

    A Neural Algorithm of Artistic Style 26 aug 2015 arxiv


    3.3   物體跟蹤

    End-to-end representation learning for Correlation Filter based tracking 20 apr 2017 arxiv


    3.4   視覺問答

    VQA: Visual Question Answering 3 may 2015


    3.5   圖像分割

    Dilated Residual Networks 22 jul 2017

SfM-Net: Learning of Structure and Motion from Video 25 apr 2017

    Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network 28 mar 2017

    Mask R-CNN 20 mar 2017 arxiv  state-of-the-art

    Learning Features by Watching Objects Move 19 dec 2016 arxiv  state-of-the-art

    RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation 20 nov 2016 arxiv

    UberNet: Training a `Universal’ Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory 7 sep 2016

    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs 2 jun 2016

    Fully Convolutional Networks for Semantic Segmentation 20 may 2016 arxiv

    Instance-aware Semantic Segmentation via Multi-task Network Cascades 14 dec 2015

    Multi-Scale Context Aggregation by Dilated Convolutions 23 nov 2015

    SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation 2 nov 2015

    U-Net: Convolutional Networks for Biomedical Image Segmentation 18 may 2015

    Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs 22 dec 2014

    Learning Rich Features from RGB-D Images for Object Detection and Segmentation 22 jul 2014


    3.6   文本識別

    OCR Error Correction Using Character Correction and Feature-Based Word Classification 21 apr 2016

    Recursive Recurrent Nets with Attention Modeling for OCR in the Wild 9 mar 2016

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images 26 jan 2016

    Efficient Scene Text Localization and Recognition with Local Character Refinement 14 apr 2015

    Reading Text in the Wild with Convolutional Neural Networks 4 dec 2014

Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition 9 jun 2014


    3.7   大腦計算機交互

    Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG 15 mar 2017

    Encoding Voxels with Deep Learning 2 dec 2015

    Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream 8 jul 2015


    3.8   自動駕駛

    Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art 18 apr 2017

    End to End Learning for Self-Driving Cars 25 apr 2016


    3.9   物體識別

    Focal Loss for Dense Object Detection 7 aug 2017

    Introspective Classifier Learning: Empower Generatively 25 apr 2017

    Learning Chained Deep Features and Classifiers for Cascade in Object Detection 23 feb 2017

    DSSD : Deconvolutional Single Shot Detector 23 jan 2017 arxiv  state-of-the-art region-proposals

    YOLO9000: Better, Faster, Stronger 25 dec 2016 arxiv github state-of-the-art region-proposals

    Feature Pyramid Networks for Object Detection 9 dec 2016 arxiv  state-of-the-art

    Speed/accuracy trade-offs for modern convolutional object detectors 30 nov 2016

    Aggregated Residual Transformations for Deep Neural Networks 16 nov 2016

    Aggregated Residual Transformations for Deep Neural Networks 16 nov 2016

    Hierarchical Object Detection with Deep Reinforcement Learning 11 nov 2016 arxiv  deep-q-learning

    Xception: Deep Learning with Depthwise Separable Convolutions 7 okt 2016

    Learning to Make Better Mistakes: Semantics-aware Visual Food Recognition 1 okt 2016

    Densely Connected Convolutional Networks 25 aug 2016

    Residual Networks of Residual Networks: Multilevel Residual Networks 9 aug 2016

    Context Matters: Refining Object Detection in Video with Recurrent Neural Networks 15 jul 2016

    R-FCN: Object Detection via Region-based Fully Convolutional Networks 20 may 2016

    Training Region-based Object Detectors with Online Hard Example Mining 12 apr 2016

    T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos 9 apr 2016

    Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning 23 feb 2016

    Deep Residual Learning for Image Recognition 10 dec 2015

    SSD: Single Shot MultiBox Detector 8 dec 2015 arxiv  region-proposals

    Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) 23 nov 2015

    ParseNet: Looking Wider to See Better 15 jun 2015

    You Only Look Once: Unified, Real-Time Object Detection 8 jun 2015 arxiv  region-proposals

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 4 jun 2015 arxiv  region-proposals

    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification 6 feb 2015

    Deep Image: Scaling up Image Recognition 13 jan 2015

    Rich feature hierarchies for accurate object detection and semantic segmentation 11 nov 2013

    Selective Search for Object Recognition 11 mar 2013

    ImageNet Classification with Deep Convolutional Neural Networks 3 dec 2012 paper  getting-started

 

    3.10   標識識別

    Deep Learning Logo Detection with Data Expansion by Synthesising Context 29 dec 2016

    Automatic Graphic Logo Detection via Fast Region-based Convolutional Networks 20 apr 2016

    LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks 8 nov 2015

    DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer 7 okt 2015


    3.11   高清晰度處理

    Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network 16 sep 2016

    Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 15 sep 2016

    RAISR: Rapid and Accurate Image Super Resolution 3 jun 2016

    Perceptual Losses for Real-Time Style Transfer and Super-Resolution 27 mar 2016 arxiv

    Image Super-Resolution Using Deep Convolutional Networks 31 dec 2014


    3.12   姿態估計

    Forecasting Human Dynamics from Static Images 11 apr 2017

    Fast Single Shot Detection and Pose Estimation 19 sep 2016

    Convolutional Pose Machines 30 jan 2016

    Flowing ConvNets for Human Pose Estimation in Videos 9 jun 2015

    

    3.13   圖像標記

    Actor-Critic Sequence Training for Image Captioning 29 jun 2017

    Detecting and Recognizing Human-Object Interactions 24 apr 2017

    Deep Reinforcement Learning-based Image Captioning with Embedding Reward 12 apr 2017 arxiv  deep-q-learning

    Towards Diverse and Natural Image Descriptions via a Conditional GAN 17 mar 2017

    Temporal Tessellation: A Unified Approach for Video Analysis 21 dec 2016 arxiv

    Self-critical Sequence Training for Image Captioning 2 dec 2016

    Generation and Comprehension of Unambiguous Object Descriptions 7 nov 2015

    Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 10 feb 2015

    Long-term Recurrent Convolutional Networks for Visual Recognition and Description 17 nov 2014


    3.14   圖像壓縮

    Full Resolution Image Compression with Recurrent Neural Networks 18 aug 2016

    

    3.15   圖像合成

    A Neural Representation of Sketch Drawings 11 apr 2017

    BEGAN: Boundary Equilibrium Generative Adversarial Networks 31 mar 2017 arxiv

Improved Training of Wasserstein GANs 31 mar 2017

    Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks 30 mar 2017 arxiv

    Wasserstein GAN 26 jan 2017

RenderGAN: Generating Realistic Labeled Data 4 nov 2016

    Conditional Image Generation with PixelCNN Decoders 16 jun 2016

Pixel Recurrent Neural Networks 25 jan 2016

    Generative Adversarial Networks 10 jun 2014

    

    3.16   人臉識別

    Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition 24 okt 2016

    OpenFace: A general-purpose face recognition library with mobile applications 1 jun 2016

    Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns 9 nov 2015

    Deep Face Recognition 7 sep 2015

    Compact Convolutional Neural Network Cascade for Face Detection 6 aug 2015

    Learning Robust Deep Face Representation 17 jul 2015

    Facenet: A unified embedding for face recognition and clustering 12 jun 2015

    Multi-view Face Detection Using Deep Convolutional Neural Networks 10 feb 2015

4 語音方面

 

    4.1   語音合成

    Title Date Paper Code Labels

Deep Cross-Modal Audio-Visual Generation 26 apr 2017

    A Neural Parametric Singing Synthesizer 12 apr 2017

    Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders 5 apr 2017 arxiv

    Tacotron: Towards End-to-End Speech Synthesis 29 mar 2017 arxiv

    Deep Voice: Real-time Neural Text-to-Speech 25 feb 2017

    WaveNet: A Generative Model for Raw Audio 12 sep 2016 arxiv

5 其他

 

    5.1   未分類

    A simple neural network module for relational reasoning 5 jun 2017 arxiv  state-of-the-art

    Deep Complex Networks 27 may 2017 arxiv

    Learning to Fly by Crashing 19 apr 2017

Who Said What: Modeling Individual     Labelers Improves Classification 26 mar 2017

    Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data 18 okt 2016

    DeepMath – Deep Sequence Models for Premise Selection 14 jun 2016

    Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue 16 mar 2016

    Long Short-Term Memory 15 nov 1997

    

    5.2   正則

    Self-Normalizing Neural Networks 8 jun 2017 arxiv  state-of-the-art

    Concrete Dropout 22 may 2017 arxiv

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning 6 jun 2015

    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift 11 feb 2015

    

    5.3   神經網絡壓縮

    Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial “Bottleneck” Structure 15 aug 2016

    SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size 24 feb 2016

    Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding 1 okt 2015

    

    5.4   優化器

    Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour 8 jun 2017 arxiv  state-of-the-art

    Equilibrated adaptive learning rates for non-convex optimization 15 feb 2015

    Adam: A Method for Stochastic Optimization 22 dec 2014

    Deep learning with Elastic Averaging SGD 20 dec 2014

    ADADELTA: An Adaptive Learning Rate Method 22 dec 2012

    Advances in Optimizing Recurrent Networks 4 dec 2012

    Efficient Backprop

往期精品內容推薦:

英特爾免費精品課程推薦-深度學習基礎

純乾貨-17 分佈式深度學習原理、演算法詳細介紹

模型彙總24 –  深度學習中Attention Mechanism詳細介紹:原理、分類及應用

斯坦福大學-2017年-秋-最新深度學習基本理論課程分享

神經機器翻譯(NMT)的一些重要資源分享

模型彙總23 – 捲積神經網絡中不同型別的捲積方式介紹

AI、神經網絡、機器學習、深度學習和大資料的核心知識備忘錄分享

斯坦福大學2017年-Spring-最新強化學習(Reinforcement Learning)課程分享

模型彙總22 機器學習相關基礎數學理論、概念、模型思維導圖分享

深度學習在自然語言處理中的應用綜述

《模型彙總-20》深度學習背後的秘密:初學者指南-深度學習激活函式大全

深度學習/機器學習的處理器串列(最全_中文版)

模型彙總20-TACOTRON一種端到端的Text-to-Speech合成模型

模型彙總19 強化學習(Reinforcement Learning)演算法基礎及分類

純乾貨13 2017年-李宏毅-最新深度學習/機器學習中文視頻教程分享

掃描下方二維碼可以訂閱哦!

DeepLearning_NLP

深度學習與NLP

       商務合作請聯繫微信號:lqfarmerlq

赞(0)

分享創造快樂