Summaries of papers on Deep Learning/Computer Vision

2018

• YOLOv3: An Incremental Improvement [Paper][Review]
  • Joseph Redmon, Ali Farhadi, arxiv, 2018

2017

• DSD: Dense-Sparse-Dense training for deep neural networks [Paper][Review]

  • Song Han, Huizi Mao, Enhao Gong, Shijian Tang, William J. Dally, arxiv 2017

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [Paper][Review]

  • Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam, arxiv, 2017

• An Implementation of Faster RCNN for Region Sampling [Paper]

  • Xinlei Chen, Abhinav Gupta, arxiv, 2017

2016

• YOLO9000: Better, Faster, Stronger [Paper][Review]

  • Joseph Redmon, Ali Farhadi, arxiv, 2016

• Densely Connected Convolutional Networks [Paper][Review]

  • Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger, arxiv, 2016

• R-FCN: Object Detection via Region-based Fully Convolutional Networks [Paper][Review]

  • Jifeng Dai, Yi Li, Kaiming He, Jian Sun, arxiv, 2016

• SqueezeNet: AlexNet-level Accuracy With 50x Fewer Parameters And <0.5MB Model Size [Paper][Review]

  • Forrest N. Iandola, Song Han, Matthew W. Moskewiez, Khalid Ashraf, William J. Dally, Kurt Keutzar, arxiv, 2016

2015

• Cyclical Learning Rates for Training Neural Networks [Paper][Review]

  • Leslie N. Smith

• You Only Look Once: Unified, Real-Time Object Detection [Paper][Review]

  • Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, arxiv, 2015

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding [Paper][Review]

  • Song Han, Huizi Mao, William J. Dally, arxiv, 2015

• Deep Residual Learning for Image Recognition [Paper][Review]

  • Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, arxiv, 2015

2014

• Going Deeper with Convolutions [Paper][Review]

  • Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, arxiv, 2014

• Network in Network [Paper] [Review]

  • Min Lin, Qiang Chen, Shuicheng Yan, ICLR, 2014

• Visualizing and Understanding Convolutional Networks [Paper][Review]

  • Matthew D. Zeiler, Rob Fergus, ECCV,2014

2013

• Overfeat : Integrated Recognition, Localization and Detection using Convolutional Neural Networks [Paper][Review]

  • Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus, Yann LeCun, arxiv, 2013

• Fast Image Scanning with Deep Max-Pooling Convolutional Neural Networks [Paper][Review]

  • Alessandro Giusti, Dan C. Ciresan, Jonathan Masci, Luca M. Gambardella, Jurgen Schmidhuber, arxiv, 2013

• Some Improvements on Deep Convolutional Neural Network based Image Classification [Paper][Review]

  • Andrew G. Howard, arxiv, 2013

2012

• ImageNet Classification with Deep Convolutional Neural Networks [Paper][Review]
  • Alex Krizhevsky, Ilya Sutskever, Geoffrey Hinton, NIPS, 2012

To-Reads

• DensePose: Dense Human Pose Estimation in the Wild
• Building Machines That Learn and Think Like People
• World Models
• Wide Residual Networks
• Residual Networks of Residual Networks: Multilevel Residual Networks