A curated list of deep learning resources for computer vision, inspired by awesome-computer-vision and awesome-deep-vision. Many thanks to Jiwon Kim' great work!

Please feel free to pull requests to add papers.

• Papers
  • ImageNet Classification
  • Object Detection
  • Object Tracking
  • Semantic Segmentation
  • Object Recognition
  • Understanding CNN
  • Image Generation
  • Reinforcement Learning
  • Visual Question Answering (VQA)
  • Other Source
• Books
• Tutorials
• Blogs

• Matching Networks for One Shot Learning [Paper]
  • Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra
• Active Convolution: Learning the Shape of Convolution for Image Classification [Paper]
  • Yunho Jeon, Junmo Kim, CVPR, 2017
• Aggregated Residual Transformations for Deep Neural Networks [Paper] [Code]
  • Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He
• Convolutional Neural Fabrics [Paper] [Code]
  • Shreyas Saxena, Jakob Verbeek
• Locally Scale-Invariant Convolutional Neural Networks [Paper] [Code]
  • Angjoo Kanazawa, Abhishek Sharma, David Jacobs

• Mask R-CNN [Paper]
  • Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick, Mask R-CNN, CVPR, 2017
• Deformable Convolutional Networks [Paper] [Code]
  • Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei, Arxiv tech report, 2017
• A-Fast-RCNN: Hard positive generation via adversary for object detection [Paper] [Code]
  • Xiaolong Wang, Abhinav Shrivastava, Abhinav Gupta, CVPR, 2017
• Spatial Memory for Context Reasoning in Object Detection [Paper]
  • Xinlei Chen, Abhinav Gupta
• Learning Features by Watching Objects Move [Paper] [Code]
  • Deepak Pathak, Ross Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan
• Improving Object Detection With One Line of Code [Paper] [Code]
  • Navaneeth Bodla, Bharat Singh, Rama Chellappa, Larry S. Davis

• Deep Feature Flow for Video Recognition [Paper] [Code]
  • Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, Yichen Wei

• Fully Convolutional Instance-aware Semantic Segmentation [Paper] [Code]
  • Yi Li, Haozhi Qi, Jifeng Dai, Xiangyang Ji, Yichen Wei, CVPR, 2017 (Spotlight)
• PixelNet: Representation of the pixels, by the pixels, and for the pixels [Paper] [Code]
  • Aayush Bansal, Xinlei Chen, Bryan Russell, Abhinav Gupta, Deva Ramanan
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform [Paper]
  • Liang-Chieh Chen, Jonathan T. Barron, George Papandreou, Kevin Murphy, Alan L. Yuille

• Discovering objects and their relations from entangled scene representations [Paper]
  • David Raposo, Adam Santoro, David Barrett, Razvan Pascanu, Timothy Lillicrap, Peter Battaglia, ICLR, 2017
• Learning Spatiotemporal Features with 3D Convolutional Networks [Paper] [Code]
  • Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri

• Structured Receptive Fields in CNNs [Paper]
  • Jörn-Henrik Jacobsen, Jan van Gemert, Zhongyu Lou, Arnold W. M. Smeulders, CVPR, 2016
• Understanding image representations by measuring their equivariance and equivalence [Paper]
  • Karel Lenc, Andrea Vedaldi, CVPR, 2015
• Dynamic Filter Networks [Paper]
  • Bert De Brabandere, Xu Jia, Tinne Tuytelaars, Luc Van Gool, NIPS, 2016
• Network Dissection: Quantifying Interpretability of Deep Visual Representations [Paper]
  • David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, Antonio Torralba, CVPR, 2017 (Oral)
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima [Paper] [Code]
  • Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, Ping Tak Peter Tang, ICLR, 2017
• Auto-Encoding Variational Bayes [Paper]
  • Diederik P Kingma, Max Welling
• Intriguing properties of neural networks [Paper]
  • Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus
• Convolutional Sequence to Sequence Learning [Paper]
  • Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks [Paper] [Code]
  • Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros
• Adversarial Feature Learning [Paper] [Code]
  • Jeff Donahue, Philipp Krähenbühl, Trevor Darrell

• Playing Atari with Deep Reinforcement Learning [Paper]
  • Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller

• Inferring and Executing Programs for Visual Reasoning [Paper] [Code]
  • Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Judy Hoffman, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick

• Newly published papers (< 6 months) which are worth reading
  • terryum
• Recent Submissions: Computer Vision and Pattern Recognition
  • arXiv.org
• DeepMind
  • DeepMind's publications

• Free Online Books
  • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
  • Neural Networks and Deep Learning by Michael Nielsen
  • Deep Natural Language Processing by Hilary Term 2017 at the University of Oxford

• UFDL, Unsupervised Feature Learning and Deep Learning
• Distill, a modern medium for presenting research
• GAN, Generative Adversarial Networks, NIPS 2016 Tutorial
• Edward, Edward provides a testbed for rapid experimentation and research with probabilistic models

• Andrej Karpathy's blog
• Colah's blog
• WILDML
• Google Research Blog