Deep Learning in the Wild

Deep learning with neural networks is applied by an increasing number of people outside of classic research environments, due to the vast success of the methodology on a wide range of machine perception tasks. While this interest is fueled by beautiful success stories, practical work in deep learning on novel tasks without existing baselines remains challenging. This paper explores the specific challenges arising in the realm of real world tasks, based on case studies from research & development in conjunction with industry, and extracts lessons learned from them. It thus fills a gap between the publication of latest algorithmic and methodical developments, and the usually omitted nitty-gritty of how to make them work. Specifically, we give insight into deep learning projects on face matching, print media monitoring, industrial quality control, music scanning, strategy game playing, and automated machine learning, thereby providing best practices for deep learning in practice.

[1]  Omkar M. Parkhi,et al.  VGGFace2: A Dataset for Recognising Faces across Pose and Age , 2017, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[2]  Timnit Gebru,et al.  Fine-Grained Recognition in the Wild: A Multi-task Domain Adaptation Approach , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Carlos E Perez.  The Deep Learning AI Playbook: Strategy for Disruptive Artificial Intelligence , 2017 .

[4]  Andrew Y. Ng,et al.  MURA Dataset: Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs , 2017, ArXiv.

[5]  Abdenour Hadid,et al.  An original face anti-spoofing approach using partial convolutional neural network , 2016, 2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA).

[6]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[7]  Tieniu Tan,et al.  Live face detection based on the analysis of Fourier spectra , 2004, SPIE Defense + Commercial Sensing.

[8]  Shai Shalev-Shwartz,et al.  Online Learning and Online Convex Optimization , 2012, Found. Trends Mach. Learn..

[9]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[10]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[11]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[12]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[13]  Jürgen Schmidhuber,et al.  DeepScores-A Dataset for Segmentation, Detection and Classification of Tiny Objects , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[14]  Shaohuai Shi,et al.  Performance Evaluation of Deep Learning Tools in Docker Containers , 2017, 2017 3rd International Conference on Big Data Computing and Communications (BIGCOM).

[15]  Arvind Satyanarayan,et al.  The Building Blocks of Interpretability , 2018 .

[16]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[19]  Min Bai,et al.  Deep Watershed Transform for Instance Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[22]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[23]  Jukka Komulainen,et al.  Face anti-spoofing based on color texture analysis , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[24]  Sergio Escalera,et al.  Design of the 2015 ChaLearn AutoML challenge , 2015, IJCNN.

[25]  Atsuto Maki,et al.  A systematic study of the class imbalance problem in convolutional neural networks , 2017, Neural Networks.

[26]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[27]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[28]  Friedhelm Schwenker,et al.  Trace and Detect Adversarial Attacks on CNNs Using Feature Response Maps , 2018, ANNPR.

[29]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[30]  Randal S. Olson,et al.  Automating Biomedical Data Science Through Tree-Based Pipeline Optimization , 2016, EvoApplications.

[31]  Jürgen Schmidhuber,et al.  Multi-column deep neural network for traffic sign classification , 2012, Neural Networks.

[32]  Junjie Yan,et al.  A face antispoofing database with diverse attacks , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[33]  Hong Li,et al.  A liveness detection method for face recognition based on optical flow field , 2009, 2009 International Conference on Image Analysis and Signal Processing.

[34]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[35]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[36]  A. Ng,et al.  MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs. , 2017 .

[37]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[38]  Marcello Pelillo,et al.  Transductive Label Augmentation for Improved Deep Network Learning , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[39]  Anil K. Jain,et al.  Secure Face Unlock: Spoof Detection on Smartphones , 2016, IEEE Transactions on Information Forensics and Security.

[40]  Aaron Klein,et al.  Efficient and Robust Automated Machine Learning , 2015, NIPS.

[41]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[42]  Naftali Tishby,et al.  Opening the Black Box of Deep Neural Networks via Information , 2017, ArXiv.

[43]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[45]  K. Harshika.  Image Quality Assessment for Fake Biometric Detection : Application to Iris , Fingerprint , and Face Recognition , 2017 .

[46]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[47]  Matti Pietikäinen,et al.  Face spoofing detection from single images using micro-texture analysis , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[48]  Jakub W. Pachocki,et al.  Emergent Complexity via Multi-Agent Competition , 2017, ICLR.

[49]  Xia Liu,et al.  A Survey of Distributed Message Broker Queues , 2017, ArXiv.

[50]  Weihong Deng,et al.  Learning temporal features using LSTM-CNN architecture for face anti-spoofing , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[51]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[52]  Jürgen Schmidhuber,et al.  Deep Watershed Detector for Music Object Recognition , 2018, ISMIR.

[53]  Sergio Escalera,et al.  A brief Review of the ChaLearn AutoML Challenge: Any-time Any-dataset Learning without Human Intervention , 2016, AutoML@ICML.

[54]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[55]  Xiaoming Liu,et al.  Face anti-spoofing using patch and depth-based CNNs , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[56]  Stan Z. Li,et al.  Learn Convolutional Neural Network for Face Anti-Spoofing , 2014, ArXiv.

[57]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[58]  Thilo Stadelmann,et al.  Beyond ImageNet: Deep Learning in Industrial Practice , 2019, Applied Data Science.

[59]  Yang Song,et al.  Improving the Robustness of Deep Neural Networks via Stability Training , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[60]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[61]  Sébastien Marcel,et al.  On the effectiveness of local binary patterns in face anti-spoofing , 2012, 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG).

[62]  Carlos Guedes,et al.  Optical music recognition: state-of-the-art and open issues , 2012, International Journal of Multimedia Information Retrieval.

[63]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[64]  Jaspreet Kaur,et al.  An Efficient Blood Vessel Detection Algorithm For Retinal Images Using Local Entropy Thresholding , 2012 .

[65]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[66]  Ivan Lanese,et al.  Microservices: How To Make Your Application Scale , 2017, Ershov Informatics Conference.

[67]  Benjamin Bruno Meier,et al.  Fully Convolutional Neural Networks for Newspaper Article Segmentation , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).