一句话：提出实例级 DNN 可视化与解释工具 NeuralVis，帮助软件工程师理解模型行为并识别关键预测特征。
深度神经网络已被广泛用于软件工程任务并嵌入应用，但其由数据驱动训练出的内部逻辑难以被软件工程师分析和理解。本文提出实例级可视化工具 NeuralVis，用于可视化与解释 DNN 模型。该工具支持四类能力：展示模型结构（神经元、层与连接）、展示数据变换过程、集成对抗攻击算法生成测试输入，以及比较不同输入在中间层的输出。作者在 LeNet 与 VGG-12 两个经典模型上开展了十人任务型用户研究。结果表明，NeuralVis 能帮助工程师识别决定预测结果的关键特征。
Deep Neural Network(DNN) techniques have been prevalent in software engineering. They are employed to facilitate various software engineering tasks and embedded into many software applications. However, because DNNs are built upon a rich data-driven programming paradigm that employs plenty of labeled data to train a set of neurons to construct the internal system logic, analyzing and understanding their behaviors becomes a difficult task for software engineers. In this paper, we present an instance-based visualization tool for DNN, namely NeuralVis, to support software engineers in visualizing and interpreting deep learning models. NeuralVis is designed for: 1). visualizing the structure of DNN models, i.e., neurons, layers, as well as connections; 2). visualizing the data transformation process; 3). integrating existing adversarial attack algorithms for test input generation; 4). comparing intermediate layers' outputs of different inputs. To demonstrate the effectiveness of NeuralVis, we design a task-based user study involving ten participants on two classic DNN models, i.e., LeNet and VGG-12. The result shows NeuralVis can assist engineers in identifying critical features that determine the prediction results. Video: https://youtu.be/solkJri4Z44
DOI 原文 ·
@inproceedings{paperbot5313,
title = {NeuralVis: Visualizing and Interpreting Deep Learning Models},
author = {Xufan Zhang and Ziyue Yin and Yang Feng and Qingkai Shi and Jia Liu and Zhenyu Chen},
booktitle = {ASE},
year = {2019},
doi = {10.1109/ase.2019.00113}
}