This paper proposes a novel hue-like angular parameter to model the structure
of deep convolutional neural network (CNN) activation space, referred to as the
{\em activation hue}, for the purpose of regularizing models for more effective
learning. The activation hue generalizes the notion of color hue angle in
standard 3-channel RGB intensity space to $N$-channel activation space. A
series of observations based on nearest neighbor indexing of activation vectors
with pre-trained networks indicate that class-informative activations are
concentrated about an angle $\theta$ in both the $(x,y)$ image plane and in
multi-channel activation space. A regularization term in the form of hue-like
angular $\theta$ labels is proposed to complement standard one-hot loss.
Training from scratch using combined one-hot + activation hue loss improves
classification performance modestly for a wide variety of classification tasks,
including ImageNet.

该论文提出了一种新的色调类似的角度参数来模型化深度卷积神经网络（CNN）激活空间的结构，称为激活色调，以实现更有效的学习的目的。通过对预训练网络的激活向量进行最近邻索引的一系列观察表明，类别信息激活在图像平面上的角度 θ 以及多通道激活空间中集中。提出了一种类似色调角度 θ 标签的正则化术语，以补充标准的 one-hot 损失。使用组合的 one-hot + 激活色调损失从头开始训练，在包括 ImageNet 在内的各种分类任务中略微改进了分类性能。