Timezone: »
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result--for example, how sensitive a prediction of “zebra” is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.
Author Information
Been Kim (Google)
Martin Wattenberg (Google)
Justin Gilmer (Google Brain)
Carrie Cai
James Wexler (Google)
Fernanda Viégas (Google)
Rory sayres (Google)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) »
Fri. Jul 13th 07:30 -- 07:50 AM Room Victoria
More from the Same Authors
-
2023 Poster: Scaling Vision Transformers to 22 Billion Parameters »
Mostafa Dehghani · Josip Djolonga · Basil Mustafa · Piotr Padlewski · Jonathan Heek · Justin Gilmer · Andreas Steiner · Mathilde Caron · Robert Geirhos · Ibrahim Alabdulmohsin · Rodolphe Jenatton · Lucas Beyer · Michael Tschannen · Anurag Arnab · Xiao Wang · Carlos Riquelme · Matthias Minderer · Joan Puigcerver · Utku Evci · Manoj Kumar · Sjoerd van Steenkiste · Gamaleldin Elsayed · Aravindh Mahendran · Fisher Yu · Avital Oliver · Fantine Huot · Jasmijn Bastings · Mark Collier · Alexey Gritsenko · Vighnesh N Birodkar · Cristina Vasconcelos · Yi Tay · Thomas Mensink · Alexander Kolesnikov · Filip Pavetic · Dustin Tran · Thomas Kipf · Mario Lucic · Xiaohua Zhai · Daniel Keysers · Jeremiah Harmsen · Neil Houlsby -
2023 Oral: Scaling Vision Transformers to 22 Billion Parameters »
Mostafa Dehghani · Josip Djolonga · Basil Mustafa · Piotr Padlewski · Jonathan Heek · Justin Gilmer · Andreas Steiner · Mathilde Caron · Robert Geirhos · Ibrahim Alabdulmohsin · Rodolphe Jenatton · Lucas Beyer · Michael Tschannen · Anurag Arnab · Xiao Wang · Carlos Riquelme · Matthias Minderer · Joan Puigcerver · Utku Evci · Manoj Kumar · Sjoerd van Steenkiste · Gamaleldin Elsayed · Aravindh Mahendran · Fisher Yu · Avital Oliver · Fantine Huot · Jasmijn Bastings · Mark Collier · Alexey Gritsenko · Vighnesh N Birodkar · Cristina Vasconcelos · Yi Tay · Thomas Mensink · Alexander Kolesnikov · Filip Pavetic · Dustin Tran · Thomas Kipf · Mario Lucic · Xiaohua Zhai · Daniel Keysers · Jeremiah Harmsen · Neil Houlsby -
2020 : Keynote #5 Justin Gilmer »
Justin Gilmer -
2020 Workshop: ML Interpretability for Scientific Discovery »
Subhashini Venugopalan · Michael Brenner · Scott Linderman · Been Kim -
2020 Poster: Concept Bottleneck Models »
Pang Wei Koh · Thao Nguyen · Yew Siang Tang · Stephen Mussmann · Emma Pierson · Been Kim · Percy Liang -
2019 Workshop: Uncertainty and Robustness in Deep Learning »
Sharon Yixuan Li · Dan Hendrycks · Thomas Dietterich · Balaji Lakshminarayanan · Justin Gilmer -
2019 Poster: Direct Uncertainty Prediction for Medical Second Opinions »
Maithra Raghu · Katy Blumer · Rory sayres · Ziad Obermeyer · Bobby Kleinberg · Sendhil Mullainathan · Jon Kleinberg -
2019 Poster: Adversarial Examples Are a Natural Consequence of Test Error in Noise »
Justin Gilmer · Nicolas Ford · Nicholas Carlini · Ekin Dogus Cubuk -
2019 Oral: Direct Uncertainty Prediction for Medical Second Opinions »
Maithra Raghu · Katy Blumer · Rory sayres · Ziad Obermeyer · Bobby Kleinberg · Sendhil Mullainathan · Jon Kleinberg -
2019 Oral: Adversarial Examples Are a Natural Consequence of Test Error in Noise »
Justin Gilmer · Nicolas Ford · Nicholas Carlini · Ekin Dogus Cubuk -
2017 Poster: Neural Message Passing for Quantum Chemistry »
Justin Gilmer · Samuel Schoenholz · Patrick F Riley · Oriol Vinyals · George Dahl -
2017 Talk: Neural Message Passing for Quantum Chemistry »
Justin Gilmer · Samuel Schoenholz · Patrick F Riley · Oriol Vinyals · George Dahl -
2017 Poster: Input Switched Affine Networks: An RNN Architecture Designed for Interpretability »
Jakob Foerster · Justin Gilmer · Jan Chorowski · Jascha Sohl-Dickstein · David Sussillo -
2017 Talk: Input Switched Affine Networks: An RNN Architecture Designed for Interpretability »
Jakob Foerster · Justin Gilmer · Jan Chorowski · Jascha Sohl-Dickstein · David Sussillo