# Visualizing and Comparing Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1412.6631 · HTML: https://mlsanity.com/paper/1412.6631/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2014.

## Built on by (most cited first, 4 of 4)

- [GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps](https://mlsanity.com/paper/2109.00951/) (2021)
- [Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training](https://mlsanity.com/paper/2406.01969/) (2024)
- [Visualizing the embedding space to explain the effect of knowledge distillation](https://mlsanity.com/paper/2110.04483/) (2021)
- [On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations](https://mlsanity.com/paper/2401.09518/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger architectures. Though CNNs achieved promising external classification behavior, understanding of their internal work mechanism is still limited. In this work, we attempt to understand the internal work mechanism of CNNs by probing the internal representations in two comprehensive aspects, i.e., visualizing patches in the representation spaces constructed by different layers, and visualizing visual information kept in each layer. We further compare CNNs with different depths and show the advantages brought by deeper architecture.