Hayoung Eom  Heeyoul Choi

10.5626/JOK.2021.48.7.774

trainable pooling

Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-sampling methods. In addition to the two pooling methods, however, there are many other pooling types, such as geometric average, harmonic average, among others. Since it is not easy for algorithms to find the best pooling method, usually the pooling types are predefined, which might not be optimal for different tasks. As other parameters in deep learning, however, the type of pooling can be driven by data for a given task. In this paper, we propose α-integration pooling (αI-pooling), which has a trainable parameter α to find the type of pooling. αI-pooling is a general pooling method including max-pooling and arithmetic average-pooling as a special case, depending on the parameter α. Experiments show that αI-pooling outperforms other pooling methods, in image recognition tasks. Also, it turns out that each layer has a different optimal pooling type.