Switchable Whitening for Deep Representation Learning
International Conference on Computer Vision, pp. 1863-1871, 2019.
Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying ...更多