December 06, 2021
The filters learned by Convolutional Neural Networks (CNNs) and the feature maps these filters compute are sensitive to convolution arithmetic. Several architectural choices that dictate this arithmetic can result in feature-map artifacts. These artifacts can interfere with the downstream task and impact the accuracy and robustness. We provide a number of visual-debugging means to surface feature-map artifacts and to analyze how they emerge in CNNs. Our means help analyze the impact of these artifacts on the weights learned by the model. Guided by our analysis, model developers can make informed architectural choices that can verifiably mitigate harmful artifacts and improve the model’s accuracy and its shift robustness.
Written by
Bilal Alsallakh
Vivek Miglani
Shubham Muttepawar
Edward Wang (AI Infra)
Sara Zhang
David Adkins
Orion Reblitz-Richardson
Publisher
NeurIPS Workshop
December 06, 2021
Yinglong Xia
December 06, 2021
December 06, 2021
Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollar, Ross Girshick
December 06, 2021
December 06, 2021
Weizhe Hua, Yichi Zhang, Chuan Guo, Zhiru Zhang, Edward Suh
December 06, 2021
December 06, 2021
Takanori Maehara, Hoang NT
December 06, 2021