[论文阅读]Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks

ILRVRC 2015 scese classification challenge第一。
arxiv: https://arxiv.org/abs/1512.05830
ECCV2016:
在类别不平衡时的采样策略：
>

Class-aware Sampling. To address this issue, we apply a sampling strategy, named “class-aware sampling”, during training. We aim to fill a mini-batch as uniform as possible with respect to classes, and prevent the same example and class from always appearing in a permanent order. In practice, we use two types of lists, an iteration, we first sample a class X in the class list, then sample an image in the per-class image list of class X. When reaching the end of the per-class image list of class X, a shuffle operation is performed to reorder the images of class X. When reaching the end of class list, a strategy to effectively tackle the non-uniform class distribution, and the gain of accuracy on the validation set is about 0.6%.

有两个列表，一个类别列表X，一个每类列表的样本列表Y。在每次取mini-batch时，先取一个X,再取一个Y中对应的一个样本，即获得一张图片用于mini-batch。往后遍历X，依次类推获得mini-batch，用以训练迭代。若X遍历完毕，再打乱X，再从头遍历X。若Y中某一类样本遍历完毕，则打乱该列样本，下次取该列类别样本时，从该列头开始取。