Understanding the role of individual units in a deep neural network

Author:

Bau DavidORCID,Zhu Jun-Yan,Strobelt Hendrik,Lapedriza Agata,Zhou BoleiORCID,Torralba Antonio

Abstract

Deep neural networks excel at finding hierarchical representations that solve complex tasks over large datasets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image editing.

Funder

Defense Sciences Office, DARPA

National Science Foundation

University Grants Committee

Publisher

Proceedings of the National Academy of Sciences

Subject

Multidisciplinary

Reference61 articles.

1. B. Zhou , A. Khosla , A. Lapedriza , A. Oliva , A. Torralba , Object detectors emerge in deep scene CNNs. arXiv:1412.6856 (22 December 2014).

2. M. D. Zeiler , R. Fergus , “Visualizing and understanding convolutional networks” in European Conference on Computer Vision (Springer, Berlin, Germany, 2014), pp. 818–833.

3. A. Mahendran , A. Vedaldi , “Understanding deep image representations by inverting them” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, New York, NY, 2015), pp. 5188–5196.

4. The building blocks of interpretability;Olah;Distill,2018

5. A. Bau , Identifying and controlling important neurons in neural machine translation. https://openreview.net/pdf?id=H1z-PsR5KX. Accessed 24 August 2020.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3