Visualizing and Understanding Convolutional Networks

Abstract

This paper addressed clear understanding of why CNNs
perform so well and how they might be improved

1.Introduction

we propose uses a multi-layered Deconvolutional Network (deconvnet), to project the feature activations back to the input pixel space.

1.1 Related work

Our visualizations differ in that they are not just crops of input images, but rather top-down projections that reveal structures within each patch that stimulate a particular feature map.

2.Approach

2.1 Visualization with a Deconvnet

A deconvnet can be thought of as a convnet model that uses the same components (filtering, pooling) but in reverse, so instead of mapping pixels to features does the opposite.