activity
20172021
most citedCaptum: A unified and generic model interpretability library for PyTorch

649 citations · 898 across the 6 of their papers we have counts for

collaborators

9 papers

cs.SE202210 cited

Prescriptive and Descriptive Approaches to Machine-Learning Transparency

David Adkins, Bilal Alsallakh, Adeel Cheema +7

Specialized documentation techniques have been developed to communicate key facts about machine-learning (ML) systems and the datasets and models they rely on. Techniques such as D…

cs.CV20221 cited

A Tour of Visualization Techniques for Computer Vision Datasets

Bilal Alsallakh, Pamela Bhattacharya, Vanessa Feng +4

We survey a number of data visualization techniques for analyzing Computer Vision (CV) datasets. These techniques help us understand properties and latent patterns in such data, by…

cs.LG20213 cited

Investigating sanity checks for saliency maps with image and text classification

Narine Kokhlikyan, Vivek Miglani, Bilal Alsallakh +2

Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text mod…

cs.CV2020

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…

cs.CV202032 cited

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…

cs.LG2020649 cited

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…