探索卷积神经网络在宽尺度范围内泛化到未见尺度的能力
Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges
AI总结：
本研究通过理论分析和实验评估，提出新型中央凹尺度通道架构（FovMax/FovAvg），在宽尺度范围内实现卷积网络对未见尺度的有效泛化，并在小样本场景中取得改进。
摘要：
处理大尺度变化的能力对于许多现实世界的视觉任务至关重要。在深度网络中处理尺度的一种直接方法是在一组尺度通道中同时以多个尺度处理图像。原则上，通过在尺度通道之间使用权重共享以及对尺度通道输出进行最大或平均池化，可以实现尺度不变性。然而，这种尺度通道网络在显著尺度范围内泛化到训练集中未出现尺度的能力此前尚未被探索。因此，我们对尺度通道网络的不变性和协方差性质进行了理论分析，并对不同类型的尺度通道网络泛化到未见尺度的能力进行了实验评估。我们识别了先前方法的局限性，并提出了一种新型的中央凹尺度通道架构，其中尺度通道以递减的分辨率处理图像中逐渐增大的部分。我们提出的FovMax和FovAvg网络在尺度范围为8的情况下，即使在单一尺度训练数据上训练时也表现几乎相同，并且在小样本场景中也带来了改进。
英文摘要：
The ability to handle large scale variations is crucial for many real world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invariance can then, in principle, be achieved by using weight sharing between the scale channels together with max or average pooling over the outputs from the scale channels. The ability of such scale channel networks to generalise to scales not present in the training set over significant scale ranges has, however, not previously been explored. We, therefore, present a theoretical analysis of invariance and covariance properties of scale channel networks and perform an experimental evaluation of the ability of different types of scale channel networks to generalise to previously unseen scales. We identify limitations of previous approaches and propose a new type of foveated scale channel architecture, where the scale channels process increasingly larger parts of the image with decreasing resolution. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single scale training data, and do also give improvements in the small sample regime.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
