Understanding the role of individual units in a deep neural network
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 hidde...
Main Authors: | Bau, David, Zhu, Jun-Yan, Strobelt, Hendrik, Lapedriza Garcia, Agata, Zhou, Bolei, Torralba, Antonio |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
Proceedings of the National Academy of Sciences
2021
|
Online Access: | https://hdl.handle.net/1721.1/130269 |
Similar Items
-
Learning Deep Features for Discriminative Localization
by: Zhou, Bolei, et al.
Published: (2017) -
Object detectors emerge in Deep Scene CNNs
by: Zhou, Bolei, et al.
Published: (2015) -
Learning Deep Features for Scene Recognition using Places Database
by: Zhou, Bolei, et al.
Published: (2015) -
Semantic photo manipulation with a generative image prior
by: Bau, David, et al.
Published: (2021) -
Places: A 10 Million Image Database for Scene Recognition
by: Zhou, Bolei, et al.
Published: (2019)