论文标题
网络内的增强
Augmentation Inside the Network
论文作者
论文摘要
在本文中，我们介绍了网络内部的增强，该方法模拟了卷积神经网络中间特征的计算机视觉问题的数据增强技术。我们执行这些转换，改变通过网络的数据流，并在可能的情况下共享共同的计算。我们的方法使我们能够获得比使用标准测试时间增强（TTA）技术更好的速度准确性权衡调整，并获得更好的结果。此外，当与测试时间增加相结合时，我们的方法可以进一步提高模型性能。我们在ImageNet-2012和CIFAR-100数据集上验证我们的方法进行图像分类。我们提出的修改比翻转测试时间增强快30％，并为CIFAR-100获得相同的结果。
In this paper, we present augmentation inside the network, a method that simulates data augmentation techniques for computer vision problems on intermediate features of a convolutional neural network. We perform these transformations, changing the data flow through the network, and sharing common computations when it is possible. Our method allows us to obtain smoother speed-accuracy trade-off adjustment and achieves better results than using standard test-time augmentation (TTA) techniques. Additionally, our approach can improve model performance even further when coupled with test-time augmentation. We validate our method on the ImageNet-2012 and CIFAR-100 datasets for image classification. We propose a modification that is 30% faster than the flip test-time augmentation and achieves the same results for CIFAR-100.
