where_to_start.md

Papers and books to read to start deep learning

This list of papers provide a good introduction to deep learning in computer vision field.

Most popular network architectures

• AlexNet https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks
• VGG16 https://arxiv.org/abs/1409.1556
• GoogLeNet (Inception) https://arxiv.org/abs/1409.4842
• ResNet (Residual Network) https://arxiv.org/abs/1512.03385
• DenseNet https://arxiv.org/abs/1608.06993
• Dual Path Network https://arxiv.org/abs/1707.01629

Object detection

• Overview article https://blog.athelas.com/a-brief-history-of-cnns-in-image-segmentation-from-r-cnn-to-mask-r-cnn-34ea83205de4
• R-CNN https://arxiv.org/abs/1311.2524
• Fast RCNN https://arxiv.org/abs/1504.08083
• Faster RCNN https://arxiv.org/abs/1506.01497
• YOLO https://arxiv.org/abs/1506.02640
• YOLO 9000 https://arxiv.org/abs/1612.08242
• SSD https://arxiv.org/abs/1512.02325

Segmentatoin

• FCN https://arxiv.org/abs/1605.06211
• UNet https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/
• 3D UNet: https://arxiv.org/abs/1606.06650
• (3D) VNet: https://arxiv.org/abs/1606.04797
• Mask RCNN https://arxiv.org/abs/1703.06870
• Polygon RNN https://arxiv.org/pdf/1704.05548.pdf
• MultiPath Network https://arxiv.org/abs/1604.02135
• DeepMask https://arxiv.org/abs/1506.06204
• SharpMask https://arxiv.org/abs/1603.08695

Books on deep learning

• Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, http://www.deeplearningbook.org/
• Deep Learning with Python, Francois Chollet
• Deep Reinforcement Learning Hands-On, Maxim Lapan
• Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto
• The Elements of Statistical Learning, 2nd Edition (ESLII, very mathematical on ML)
  • https://web.stanford.edu/~hastie/Papers/ESLII.pdf
• Introduction of Statistical Learning (ISL, dumbed down version of ESLII)
  • http://www-bcf.usc.edu/~gareth/ISL/