Skip to content
This repository has been archived by the owner on Apr 5, 2024. It is now read-only.

Latest commit

 

History

History
495 lines (394 loc) · 37.6 KB

README.md

File metadata and controls

495 lines (394 loc) · 37.6 KB

Deep Learning Papers by task

Papers about deep learning ordered by task, date. For each paper there is a permanent link, which is either to Arxiv.org or to a copy of the original paper in this repository.

Table of Contents

  1. Code

    1.1. Code Generation

    1.2. Malware Detection and Security

  2. Text

    2.1. Summarization

    2.2. Taskbots

    2.3. Classification

    2.4. Question Answering

    2.5. Sentiment Analysis

    2.6. Translation

    2.7. Chatbots

    2.8. Reasoning

    2.9. Language Representation

  3. Visual

    3.1. Gaming

    3.2. Style Transfer

    3.3. Object Tracking

    3.4. Visual Question Answering

    3.5. Image Segmentation

    3.6. Text (in the Wild) Recognition

    3.7. Brain Computer Interfacing

    3.8. Self-Driving Cars

    3.9. Object Recognition

    3.10. Logo Recognition

    3.11. Super Resolution

    3.12. Pose Estimation

    3.13. Image Captioning

    3.14. Image Compression

    3.15. Image Synthesis

    3.16. Face Recognition

    3.17. Image Composition

    3.18. Scene Graph Parsing

    3.19. Video Deblurring

    3.20. Depth Perception

    3.21. 3D Reconstruction

    3.22. Vision Representation

  4. Audio

    4.1. Audio Synthesis

  5. Other

    5.1. Unclassified

    5.2. Regularization

    5.3. Neural Network Compression

    5.4. Optimizers

Code

Code Generation

Title Date Paper Code
DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning 25 apr 2017 arxiv
A Syntactic Neural Model for General-Purpose Code Generation 6 apr 2017 arxiv
RobustFill: Neural Program Learning under Noisy I/O 21 mar 2017 arxiv
DeepFix: Fixing Common C Language Errors by Deep Learning 12 feb 2017 paper
DeepCoder: Learning to Write Programs 7 nov 2016 arxiv
Neuro-Symbolic Program Synthesis 6 nov 2016 arxiv
Deep API Learning 27 may 2016 arxiv

Malware Detection and Security

Title Date Paper Code
PassGAN: A Deep Learning Approach for Password Guessing 1 sep 2017 arxiv
Deep Android Malware Detection 22 mar 2016 paper github
Droid-Sec: Deep Learning in Android Malware Detection 17 aug 2014 paper github

Text

Summarization

Title Date Paper Code
A Deep Reinforced Model for Abstractive Summarization 11 may 2017 arxiv
Get To The Point: Summarization with Pointer-Generator Networks 14 apr 2017 arxiv
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents 14 nov 2016 arxiv

Taskbots

Title Date Paper Code
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning 10 apr 2017 arxiv github
End-to-End Task-Completion Neural Dialogue Systems 3 mar 2017 arxiv github

Classification

Title Date Paper Code
A Large Self-Annotated Corpus for Sarcasm 19 apr 2017 arxiv
ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge 11 apr 2017 arxiv
Bilateral Multi-Perspective Matching for Natural Language Sentences 13 feb 2017 arxiv
FastText.zip: Compressing text classification models 12 dec 2016 arxiv
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge 12 dec 2016 arxiv
A Simple but Tough-to-Beat Baseline for Sentence Embeddings 4 nov 2016 paper github
Enriching Word Vectors with Subword Information 15 jul 2016 arxiv
From Word Embeddings To Document Distances 6 jul 2016 paper github
Bag of Tricks for Efficient Text Classification 6 jul 2016 arxiv
Character-level Convolutional Networks for Text Classification 4 sep 2015 arxiv
GloVe: Global Vectors for Word Representation 25 may 2015 paper github
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks 28 feb 2015 arxiv
Distributed Representations of Sentences and Documents 16 may 2014 arxiv
Efficient Estimation of Word Representations in Vector Space 16 jan 2013 arxiv
SimHash: Hash-based Similarity Detection 13 dec 2007 paper

Question Answering

Title Date Paper Code
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models 30 may 2017 arxiv github

Sentiment Analysis

Title Date Paper Code
Rationalizing Neural Predictions 13 jun 2016 arxiv
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank 18 okt 2013 paper

Translation

Title Date Paper Code
Attention Is All You Need 12 jun 2017 arxiv
Convolutional Sequence to Sequence Learning 8 may 2017 arxiv github
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation 14 nov 2016 arxiv
A Convolutional Encoder Model for Neural Machine Translation 7 nov 2016 arxiv
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation 26 sep 2016 arxiv
Neural Machine Translation by Jointly Learning to Align and Translate 1 sep 2014 arxiv

Chatbots

Title Date Paper Code
A Deep Reinforcement Learning Chatbot 7 sep 2017 arxiv
A Neural Conversational Model 19 jun 2015 arxiv github

Reasoning

Title Date Paper Code
NeuroSAT: Learning a SAT Solver from Single-Bit Supervision 5 jan 2019 arxiv github
Tracking the World State with Recurrent Entity Networks 12 dec 2016 arxiv

Language Representation

Title Date Paper Code
Efficient Estimation of Word Representations in Vector Space 7 sep 2013 arxiv
Distributed Representations of Words and Phrases and their Compositionality 16 okt 2013 arxiv
ELMO: Deep contextualized word representations 22 Mar 2018 arxiv
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 24 may 2019 arxiv github
XLNet: Generalized Autoregressive Pretraining for Language Understanding 19 jun 2019 arxiv github
RoBERTa: A Robustly Optimized BERT Pretraining Approach 26 jul 2019 arxiv github

Visual

Gaming

Title Date Paper Code
Phase-Functioned Neural Networks for Character Control 1 may 2017 paper
Equivalence Between Policy Gradients and Soft Q-Learning 21 apr 2017 arxiv
Beating Atari with Natural Language Guided Reinforcement Learning 18 apr 2017 arxiv
Learning from Demonstrations for Real World Reinforcement Learning 12 apr 2017 arxiv
FeUdal Networks for Hierarchical Reinforcement Learning 3 mar 2017 arxiv
Overcoming catastrophic forgetting in neural networks 2 dec 2016 arxiv
Playing Doom with SLAM-Augmented Deep Reinforcement Learning 1 dec 2016 arxiv
Playing FPS Games with Deep Reinforcement Learning 18 sep 2016 arxiv
DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess 16 aug 2016 paper
Generative Adversarial Imitation Learning 10 jun 2016 arxiv
Dueling Network Architectures for Deep Reinforcement Learning 20 nov 2015 arxiv
Prioritized Experience Replay 18 nov 2015 arxiv
Human-level control through deep reinforcement learning 26 feb 2015 paper
Playing Atari with Deep Reinforcement Learning 19 dec 2013 arxiv

Style Transfer

Title Date Paper Code
The Contextual Loss for Image Transformation with Non-Aligned Data 18 jul 2018 arxiv github
Deep Photo Style Transfer 22 mar 2017 arxiv
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization 20 mar 2017 arxiv github
A Learned Representation For Artistic Style 24 okt 2016 arxiv
Instance Normalization: The Missing Ingredient for Fast Stylization 27 jul 2016 arxiv
Perceptual Losses for Real-Time Style Transfer and Super-Resolution 27 mar 2016 arxiv github
A Neural Algorithm of Artistic Style 26 aug 2015 arxiv github

Object Tracking

Title Date Paper Code
End-to-end representation learning for Correlation Filter based tracking 20 apr 2017 arxiv github

Visual Question Answering

Title Date Paper Code
VQA: Visual Question Answering 3 may 2015 arxiv

Image Segmentation

Title Date Paper Code
PointRend: Image Segmentation as Rendering 17 dec 2019 arxiv
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation 22 aug 2018 paper cvpr github
Dilated Residual Networks 22 jul 2017 paper
SfM-Net: Learning of Structure and Motion from Video 25 apr 2017 arxiv
Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network 28 mar 2017 arxiv
Mask R-CNN 20 mar 2017 arxiv
Learning Features by Watching Objects Move 19 dec 2016 arxiv
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation 20 nov 2016 arxiv github
UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory 7 sep 2016 arxiv
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs 2 jun 2016 arxiv
Fully Convolutional Networks for Semantic Segmentation 20 may 2016 arxiv github
Instance-aware Semantic Segmentation via Multi-task Network Cascades 14 dec 2015 arxiv
Multi-Scale Context Aggregation by Dilated Convolutions 23 nov 2015 arxiv
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation 2 nov 2015 arxiv
U-Net: Convolutional Networks for Biomedical Image Segmentation 18 may 2015 arxiv
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs 22 dec 2014 arxiv
Learning Rich Features from RGB-D Images for Object Detection and Segmentation 22 jul 2014 arxiv

Text (in the Wild) Recognition

Title Date Paper Code
OCR Error Correction Using Character Correction and Feature-Based Word Classification 21 apr 2016 arxiv
Recursive Recurrent Nets with Attention Modeling for OCR in the Wild 9 mar 2016 arxiv
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images 26 jan 2016 arxiv
Efficient Scene Text Localization and Recognition with Local Character Refinement 14 apr 2015 arxiv
Reading Text in the Wild with Convolutional Neural Networks 4 dec 2014 arxiv
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition 9 jun 2014 arxiv

Brain Computer Interfacing

Title Date Paper Code
Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG 15 mar 2017 arxiv
Encoding Voxels with Deep Learning 2 dec 2015 paper
Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream 8 jul 2015 paper

Self-Driving Cars

Title Date Paper Code
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art 18 apr 2017 arxiv
End to End Learning for Self-Driving Cars 25 apr 2016 arxiv

Object Recognition

Title Date Paper Code
Cascade R-CNN: High Quality Object Detection and Instance Segmentation 24 Jun 2019 arxiv github
YOLOv3: An Incremental Improvement 8 Apr 2018 arxiv github, github reimplementation
Focal Loss for Dense Object Detection 7 aug 2017 arxiv
Introspective Classifier Learning: Empower Generatively 25 apr 2017 arxiv
Learning Chained Deep Features and Classifiers for Cascade in Object Detection 23 feb 2017 arxiv
DSSD : Deconvolutional Single Shot Detector 23 jan 2017 arxiv
YOLO9000: Better, Faster, Stronger 25 dec 2016 arxiv github
Feature Pyramid Networks for Object Detection 9 dec 2016 arxiv
Speed/accuracy trade-offs for modern convolutional object detectors 30 nov 2016 arxiv
Aggregated Residual Transformations for Deep Neural Networks 16 nov 2016 arxiv
Aggregated Residual Transformations for Deep Neural Networks 16 nov 2016 arxiv
Hierarchical Object Detection with Deep Reinforcement Learning 11 nov 2016 arxiv
Xception: Deep Learning with Depthwise Separable Convolutions 7 okt 2016 arxiv
Learning to Make Better Mistakes: Semantics-aware Visual Food Recognition 1 okt 2016 paper
Densely Connected Convolutional Networks 25 aug 2016 arxiv
Residual Networks of Residual Networks: Multilevel Residual Networks 9 aug 2016 arxiv
Context Matters: Refining Object Detection in Video with Recurrent Neural Networks 15 jul 2016 arxiv
R-FCN: Object Detection via Region-based Fully Convolutional Networks 20 may 2016 arxiv
Training Region-based Object Detectors with Online Hard Example Mining 12 apr 2016 arxiv
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos 9 apr 2016 arxiv
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning 23 feb 2016 arxiv
Deep Residual Learning for Image Recognition 10 dec 2015 arxiv
SSD: Single Shot MultiBox Detector 8 dec 2015 arxiv
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) 23 nov 2015 arxiv
ParseNet: Looking Wider to See Better 15 jun 2015 arxiv
You Only Look Once: Unified, Real-Time Object Detection 8 jun 2015 arxiv
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 4 jun 2015 arxiv
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification 6 feb 2015 arxiv
Deep Image: Scaling up Image Recognition 13 jan 2015 arxiv
Rich feature hierarchies for accurate object detection and semantic segmentation 11 nov 2013 arxiv
Selective Search for Object Recognition 11 mar 2013 paper
ImageNet Classification with Deep Convolutional Neural Networks 3 dec 2012 paper

Logo Recognition

Title Date Paper Code
Deep Learning Logo Detection with Data Expansion by Synthesising Context 29 dec 2016 arxiv
Automatic Graphic Logo Detection via Fast Region-based Convolutional Networks 20 apr 2016 arxiv
LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks 8 nov 2015 arxiv
DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer 7 okt 2015 arxiv

Super Resolution

Title Date Paper Code
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network 16 sep 2016 arxiv
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 15 sep 2016 arxiv
RAISR: Rapid and Accurate Image Super Resolution 3 jun 2016 arxiv
Perceptual Losses for Real-Time Style Transfer and Super-Resolution 27 mar 2016 arxiv github
Image Super-Resolution Using Deep Convolutional Networks 31 dec 2014 arxiv

Pose Estimation

Title Date Paper Code
Forecasting Human Dynamics from Static Images 11 apr 2017 arxiv
Fast Single Shot Detection and Pose Estimation 19 sep 2016 arxiv
Convolutional Pose Machines 30 jan 2016 arxiv
Flowing ConvNets for Human Pose Estimation in Videos 9 jun 2015 arxiv

Image Captioning

Title Date Paper Code
Actor-Critic Sequence Training for Image Captioning 29 jun 2017 arxiv
Detecting and Recognizing Human-Object Interactions 24 apr 2017 arxiv
Deep Reinforcement Learning-based Image Captioning with Embedding Reward 12 apr 2017 arxiv
Towards Diverse and Natural Image Descriptions via a Conditional GAN 17 mar 2017 arxiv
Temporal Tessellation: A Unified Approach for Video Analysis 21 dec 2016 arxiv github
Self-critical Sequence Training for Image Captioning 2 dec 2016 arxiv
Generation and Comprehension of Unambiguous Object Descriptions 7 nov 2015 arxiv
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention 10 feb 2015 arxiv
Long-term Recurrent Convolutional Networks for Visual Recognition and Description 17 nov 2014 arxiv

Image Compression

Title Date Paper Code
Full Resolution Image Compression with Recurrent Neural Networks 18 aug 2016 arxiv

Image Synthesis

Title Date Paper Code
Scene Text Synthesis for Efficient and Effective Deep Network Training 26 jan 2019 arxiv
A Neural Representation of Sketch Drawings 11 apr 2017 arxiv
BEGAN: Boundary Equilibrium Generative Adversarial Networks 31 mar 2017 arxiv github
Improved Training of Wasserstein GANs 31 mar 2017 arxiv
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks 30 mar 2017 arxiv github
Wasserstein GAN 26 jan 2017 arxiv
RenderGAN: Generating Realistic Labeled Data 4 nov 2016 arxiv
Conditional Image Generation with PixelCNN Decoders 16 jun 2016 arxiv
Pixel Recurrent Neural Networks 25 jan 2016 arxiv
Generative Adversarial Networks 10 jun 2014 arxiv

Face Recognition

Title Date Paper Code
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition 24 okt 2016 paper
OpenFace: A general-purpose face recognition library with mobile applications 1 jun 2016 paper
Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns 9 nov 2015 paper
Deep Face Recognition 7 sep 2015 paper
Compact Convolutional Neural Network Cascade for Face Detection 6 aug 2015 arxiv
Learning Robust Deep Face Representation 17 jul 2015 arxiv
Facenet: A unified embedding for face recognition and clustering 12 jun 2015 paper
Multi-view Face Detection Using Deep Convolutional Neural Networks 10 feb 2015 arxiv

Image Composition

Title Date Paper Code
Auto-Retoucher(ART) — A Framework for Background Replacement and Foreground Adjustment 13 jan 2019 arxiv (brave new task) github (not able to reproduce results based on code)
Spatial Fusion GAN for Image Synthesis 14 Dec 2018 arxiv (needs revision, interesting approach however) github (currently, no code available)
Compositional GAN: Learning Conditional Image Composition 23 Aug 2018 arxiv (with respect to spatial orientation) github (currently, no code available)
ST-GAN 5 mar 2018 arxiv (with respect to spatial orientation) github
Deep Painterly Harmonization 26 Jun 2018 paper github
Deep Image Harmonization 28 feb 2017 paper github (only code for inference)
Understanding and Improving the Realism of Image Composites 1 Jul 2012 paper

Scene Graph Parsing

Title Date Paper Code
Neural Motifs: Scene Graph Parsing with Global Context 29 Mar 2018 arxiv github

Video Deblurring

Title Date Paper Code
Spatio-Temporal Filter Adaptive Network for Video Deblurring 28 Apr 2019 arxiv github (to appear)

Depth Perception

Title Date Paper Code
Learning Depth with Convolutional Spatial Propagation Network 13 Okt 2018 arxiv github
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches 18 May 2016 arxiv github

3D Reconstruction

Title Date Paper Code
Cerberus: A Multi-headed Derenderer 28 May 2019 arxiv

Vision Representation

Title Date Paper Code
VisualBERT: A Simple and Performant Baseline for Vision and Language 9 aug 2019 arxiv
Expected to appear: some paper learning an unsupervised vision representation that beats SOTA on a large number of tasks <Before the end of 2019>

Audio

Audio Synthesis

Title Date Paper Code
Deep Cross-Modal Audio-Visual Generation 26 apr 2017 arxiv
A Neural Parametric Singing Synthesizer 12 apr 2017 arxiv
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders 5 apr 2017 arxiv github
Tacotron: Towards End-to-End Speech Synthesis 29 mar 2017 arxiv github
Deep Voice: Real-time Neural Text-to-Speech 25 feb 2017 arxiv
WaveNet: A Generative Model for Raw Audio 12 sep 2016 arxiv github

Other

Unclassified

Title Date Paper Code
A simple neural network module for relational reasoning 5 jun 2017 arxiv
Deep Complex Networks 27 may 2017 arxiv github
Learning to Fly by Crashing 19 apr 2017 arxiv
Who Said What: Modeling Individual Labelers Improves Classification 26 mar 2017 arxiv
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data 18 okt 2016 arxiv
DeepMath - Deep Sequence Models for Premise Selection 14 jun 2016 arxiv
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue 16 mar 2016 arxiv
Long Short-Term Memory 15 nov 1997 paper

Regularization

Title Date Paper Code
Self-Normalizing Neural Networks 8 jun 2017 arxiv
Concrete Dropout 22 may 2017 arxiv github
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning 6 jun 2015 arxiv
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift 11 feb 2015 arxiv

Neural Network Compression

Title Date Paper Code
Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial "Bottleneck" Structure 15 aug 2016 arxiv
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size 24 feb 2016 arxiv
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding 1 okt 2015 arxiv

Optimizers

Title Date Paper Code
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour 8 jun 2017 arxiv
Equilibrated adaptive learning rates for non-convex optimization 15 feb 2015 arxiv
Adam: A Method for Stochastic Optimization 22 dec 2014 arxiv
Deep learning with Elastic Averaging SGD 20 dec 2014 arxiv
ADADELTA: An Adaptive Learning Rate Method 22 dec 2012 arxiv
Advances in Optimizing Recurrent Networks 4 dec 2012 arxiv
Efficient Backprop 1 jul 1998 paper

A note on arXiv

arXiv provides the world with access to the newest scientific developments. Open Access has a myriad of benefits, in particular, it allows science to be more efficient. Remember to think about the quality of the papers referenced. In particular, the importance of the peer-review process for science.
If you find an article on arXiv you should check if it has been peer-reviewed and published elsewhere. The authoritative version of the paper is not the version on arXiv, rather it is the published peer-reviewed version. The two versions may differ significantly.

For example, this is the case with one of the papers that I once discussed in the Text and Multimedia Mining class at Radboud:

For the selection of the papers above, I choose open access over completeness. If you find another (open) version of a paper, you are invited to make a pull request.