Transitioning between Convolutional and Fully Connected Layers in Neural Networks

TL;DR

This paper introduces a novel transition module for CNNs that learns from multiple spatial resolutions to improve breast tumor classification in digital pathology images.

Contribution

It proposes a new transition module that enhances CNNs by learning global average pooling from filters of different sizes, improving classification performance.

Findings

Transition module outperforms standard models in breast tumor classification

Demonstrated effectiveness across two independent datasets

Applicable to AlexNet and ZFNet architectures

Abstract

Digital pathology has advanced substantially over the last decade however tumor localization continues to be a challenging problem due to highly complex patterns and textures in the underlying tissue bed. The use of convolutional neural networks (CNNs) to analyze such complex images has been well adopted in digital pathology. However in recent years, the architecture of CNNs have altered with the introduction of inception modules which have shown great promise for classification tasks. In this paper, we propose a modified "transition" module which learns global average pooling layers from filters of varying sizes to encourage class-specific filters at multiple spatial resolutions. We demonstrate the performance of the transition module in AlexNet and ZFNet, for classifying breast tumors in two independent datasets of scanned histology sections, of which the transition module was superior.