SmoothGrad: removing noise by adding noise

Training with noise is equivalent to tikhonov regularization

Bishop, Chris M · 1995

Earlier work this paper cites.

Gradient-based learning applied to document recognition

LeCun, Yann, Bottou, Léon, Bengio, Yoshua, and Haffner, Patrick · 1998

Earlier work this paper cites.

Visualizing higher-layer features of a deep network

Erhan, Dumitru, Bengio, Yoshua, Courville, Aaron, and Vincent, Pascal · 2009

Earlier work this paper cites.

How to explain individual classification decisions

Baehrens, David, Schroeter, Timon, Harmeling, Stefan, Kawanabe, Motoaki, Hansen, Katja, and MÞller, Klaus-Robert · 2010

Earlier work this paper cites.

Mnist handwritten digit database

LeCun, Yann, Cortes, Corinna, and Burges, Christopher JC · 2010

Earlier work this paper cites.

Intelligible models for classification and regression

Lou, Yin, Caruana, Rich, and Gehrke, Johannes · 2012

Earlier work this paper cites.

Deep inside convolutional networks: Visualising image classification models and saliency maps

Original

Simonyan, Karen, Vedaldi, Andrea, and Zisserman, Andrew · 2013

Earlier work this paper cites.

Intriguing properties of neural networks

Original

Szegedy, Christian, Zaremba, Wojciech, Sutskever, Ilya, Bruna, Joan, Erhan, Dumitru, Goodfellow, Ian, and Fergus, Rob · 2013

Earlier work this paper cites.

Comorbidity clusters in autism spectrum disorders: an electronic health record time-series analysis

Doshi-Velez, Finale, Ge, Yaorong, and Kohane, Isaac · 2014

Earlier work this paper cites.

Comprehensible classification models: a position paper

Freitas, Alex · 2014

Cited alongside, same era.

Striving for simplicity: The all convolutional net

Original

Springenberg, Jost Tobias, Dosovitskiy, Alexey, Brox, Thomas, and Riedmiller, Martin · 2014

Cited alongside, same era.

Visualizing and understanding convolutional networks

Zeiler, Matthew D and Fergus, Rob · 2014

Cited alongside, same era.

On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation

Bach, Sebastian, Binder, Alexander, Montavon, Grégoire, Klauschen, Frederick, Müller, Klaus-Robert, and Samek, Wojciech · 2015

Cited alongside, same era.

ibcm: Interactive bayesian case model empowering humans via intuitive interaction

Kim, Been, Glassman, Elena, Johnson, Brittney, and Shah, Julie · 2015

Cited alongside, same era.

Rethinking the inception architecture for computer vision

Szegedy, Christian, Vanhoucke, Vincent, Ioffe, Sergey, Shlens, Jon, and Wojna, Zbigniew · 2016

Later among the works it cites.

Learning deep features for discriminative localization

Zhou, Bolei, Khosla, Aditya, Lapedriza, Agata, Oliva, Aude, and Torralba, Antonio · 2016

Later among the works it cites.

A new method to visualize deep neural networks

Original

Zintgraf, Luisa M., Cohen, Taco S., and Welling, Max · 2016

Later among the works it cites.

Towards a rigorous science of interpretable machine learning

Original

Doshi-Velez, Finale; Kim, Been · 2017

Closest in time.

Exploiting saliency for object segmentation from image level labels

Original

Oh, Seong Joon, Benenson, Rodrigo, Khoreva, Anna, Akata, Zeynep, Fritz, Mario, and Schiele, Bernt · 2017