# Towards Better Analysis of Deep Convolutional Neural Networks

Source: [Towards Better Analysis of Deep Convolutional Neural Networks](<https://www.sota2.com/research/paper/68fa627f1e209131ce9f99c0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:20:33.540Z

Authors: Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, Shixia Liu

Published: 2016-04-24T15:53:22.000Z

## Abstract

Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets of each neuron and the interactions between them. In particular, we introduce a hierarchical rectangle packing algorithm and a matrix reordering algorithm to show the derived features of a neuron cluster. We also propose a biclustering-based edge bundling method to reduce visual clutter caused by a large number of connections between neurons. We evaluated our method on a set of CNNs and the results are generally favorable.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1604.07043>)

[PDF](<https://arxiv.org/pdf/1604.07043.pdf>)
