Pooling Revisited: Your Receptive Field is Suboptimal

by   Dong-Hwan Jang, et al.

The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably. Many components in a neural network, such as kernel sizes and strides for convolution and pooling operations, influence the configuration of a receptive field. However, they still rely on hyperparameters, and the receptive fields of existing models result in suboptimal shapes and sizes. Hence, we propose a simple yet effective Dynamically Optimized Pooling operation, referred to as DynOPool, which optimizes the scale factors of feature maps end-to-end by learning the desirable size and shape of its receptive field in each layer. Any kind of resizing modules in a deep neural network can be replaced by the operations with DynOPool at a minimal cost. Also, DynOPool controls the complexity of a model by introducing an additional loss term that constrains computational cost. Our experiments show that the models equipped with the proposed learnable resizing module outperform the baseline networks on multiple datasets in image classification and semantic segmentation.


ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning

Extracting multi-scale information is key to semantic segmentation. Howe...

Receptive Field Size Optimization with Continuous Time Pooling

The pooling operation is a cornerstone element of convolutional neural n...

Understanding the Influence of Receptive Field and Network Complexity in Neural-Network-Guided TEM Image Analysis

Trained neural networks are promising tools to analyze the ever-increasi...

Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae

Segmentation of objects with various sizes is relatively less explored i...

Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields

The visual world is vast and varied, but its variations divide into stru...

Split-Merge Pooling

There are a variety of approaches to obtain a vast receptive field with ...

LIP: Local Importance-based Pooling

Spatial downsampling layers are favored in convolutional neural networks...