MahmoudTamam / deep-learning-papers

Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Deep Learning Papers

Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.

Object Recognition

  • Aggregated Residual Transformations for Deep Neural Networks, nov 2016, arxiv
  • Hierarchical Object Detection with Deep Reinforcement Learning, nov 2016, arxiv
  • Learning to Make Better Mistakes: Semantics-aware Visual Food Recognition, okt 2016, IBM, paper
  • T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos, aug 2016, github, arxiv
  • Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, aug 2016, Google, arxiv
  • Residual Networks of Residual Networks: Multilevel Residual Networks, aug 2016, arxiv
  • Context Matters: Refining Object Detection in Video with Recurrent Neural Networks, jul 2016, arxiv
  • Training Region-based Object Detectors with Online Hard Example Mining, apr 2016, Facebook, arxiv
  • Deep Residual Learning for Image Recognition, dec 2015, arxiv
  • SSD: Single Shot MultiBox Detector, dec 2015, Google, github, arxiv state-of-the-art
  • ParseNet: Looking Wider to See Better, jun 2015, arxiv
  • You Only Look Once: Unified, Real-Time Object Detection, jun 2015, Facebook, arxiv
  • Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, jun 2015, Microsoft/Facebook arxiv state-of-the-art
  • Selective Search for Object Recognition, 2012, paper
  • Rich feature hierarchies for accurate object detection and semantic segmentation, 2014, paper

Pose Estimation

  • Fast Single Shot Detection and Pose Estimation, sep 2016, arxiv

Face Recognition

  • Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition, paper
  • OpenFace: A general-purpose face recognition library with mobile applications, June 2016, paper
  • Deep Face Recognition, 2015, paper
  • Compact Convolutional Neural Network Cascade for Face Detection, aug 2015, arxiv
  • Learning Robust Deep Face Representation, Jul 2015, arxiv
  • FaceNet: A Unified Embedding for Face Recognition and Clustering, jun 2015, paper
  • Multi-view Face Detection Using Deep Convolutional Neural Networks, yahoo, feb 2015, arxiv

Style Transfer

  • A learned representation for artistic style, okt 2016, Google, arxiv, demo
  • Fast Style Transfer in TensorFlow, github
  • Instance Normalization: The Missing Ingredient for Fast Stylization, sept 2016, arxiv
  • A Neural Algorithm of Artistic Style, sept 2015, arxiv
  • Perceptual Losses for Real-Time Style Transfer and Super-Resolution, arxiv, github

Logo Recognition

  • Automatic Graphic Logo Detection via Fast Region-based Convolutional Networks, apr 2016, arxiv
  • Logo Localization and Recognition in Natural Images Using Homographic Class Graphs, 2016, paper
  • LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks, nov 2015, arxiv
  • DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer, okt 2015, Berkely, arxiv
  • Automatic detection of logos in video and their removal using inpainting, jul 2015, paper
  • On the Benefit of Synthetic Data for Company Logo Detection, 2015, paper
  • Fast and Robust Realtime Storefront Logo Recognition, paper
  • Scalable Logo Recognition in Real-World Images, 2011, paper

note: also includes some papers that use SIFT

Text (in the Wild) Recognition

  • COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images, jun 2016, arxiv
  • Recursive Recurrent Nets with Attention Modeling for OCR in the Wild, mar 2016, arxiv state-of-the-art
  • Efficient Scene Text Localization and Recognition with Local Character Refinement, apr 2015, arxiv
  • Reading Text in the Wild with Convolutional Neural Networks, dec 2014, arxiv
  • Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition, jun 2014, arxiv
  • Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning, 2011, paper

Image / Video Description

  • Generation and Comprehension of Unambiguous Object Descriptions, apr 2016, arxiv
  • Long-term Recurrent Convolutional Networks for Visual Recognition and Description, may 2016, arxiv

Detect key actor

  • Detecting events and key actors in multi-person videos, mar 2015, arxiv

ConvNet visualization

  • Visualizing and Understanding Convolutional Networks, Nov 2013, arxiv

Image Segmentation

  • SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, dec 2015, arxiv

Object part detection

  • Discovering the physical parts of an articulated object class from multiple videos, 2016, paper

Pedestrian Detection

  • Joint Deep Learning for Pedestrian Detection, 2013, paper

Lip Reading

  • Lip Reading in the Wild, 2016, Oxford, paper

Super Resolution

  • RAISR: Rapid and Accurate Image Super Resolution, okt 2016, Google, arxiv
  • Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network, sep 2016, Twitter, arxiv

Image Compression

  • Full Resolution Image Compression with Recurrent Neural Networks, aug 2016, Google arxiv

Automated Theorem Proving

  • DeepMath - Deep Sequence Models for Premise Selection, jun 2016, Google arxiv

Reverse Engineering

  • Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, okt 2016, arxiv
  • Stealing Machine Learning Models via Prediction APIs, aug 2016, paper



  • Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation, nov 2016, Google, arxiv
  • Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, okt 2016, Google arxiv


Architecture and optimization

  • RenderGAN: Generating Realistic Labeled Data, nov 2016, arxiv
  • Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding, feb 2016, arxiv
  • SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, feb 2016, arxiv
  • Snapshot Ensembles: Train 1, Get M for Free, 2016, paper, github

Tools for Deep Learning

  • Barrista github
  • Deep Learning 4 J github
  • Caffe: Convolutional Architecture for Fast Feature Embedding, jun 2014, github, arxiv

Tools for Papers

Data Sets

  • MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition, jul 2016, arxiv
  • Family in the Wild (FIW): A Large-scale Kinship Recognition Database, apr 2016, arxiv
  • YouTube-8M: A Large-Scale Video Classification Benchmark, sep 2016, Google, arxiv



Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.