2012-AlexNet
NIPS-Alex Krizhevsky (Geoffrey E. Hinton)
[ImageNet Classification with Deep Convolutional Neural Networks] (https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)
预处理: Subtracting the mean activity over the training set from each pixel.
2014-VGG
arXiv-K. Simonyan, A. Zisserman
[Very Deep Convolutional Networks for Large-Scale Visual Recognition] (http://www.robots.ox.ac.uk/~vgg/research/very_deep/)
The following BGR values should be subtracted: [103.939, 116.779, 123.68] for ILSVRC-2014
2015-FCN
CVPR-Jonathan Long, Evan Shelhamer
[Fully Convolutional Networks for Semantic Segmentation] (https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf)
BGR subtracted mean=(104.00698793, 116.66876762, 122.67891434) for VOC2011.
2015-ResNet
CVPR-Kaiming He
[Deep Residual Learning for Image Recognition] (https://github.com/KaimingHe/deep-residual-networks)