649 citations · 914 across the 10 of their papers we have counts for
4 papers · 1 filter
Investigating Saturation Effects in Integrated Gradients
Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh +2
Integrated Gradients has become a popular method for post-hoc model interpretability. De-spite its popularity, the composition and relative impact of different regions of the integ…
Mind the Pad -- CNNs can Develop Blind Spots
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani +2
We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematic…
Captum: A unified and generic model interpretability library for PyTorch
Narine Kokhlikyan, Vivek Miglani, Miguel Martin +8
In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and p…
Visualizing Classification Structure of Large-Scale Classifiers
Bilal Alsallakh, Zhixin Yan, Shabnam Ghaffarzadegan +2
We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show h…