NSF PAR Search | NSF Public Access Repository

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

Park, Haekyu and (May 2021, Proceedings of the AAAI Conference on Artificial Intelligence)

Full Text Available
NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks

https://doi.org/10.1109/TVCG.2021.3114858

Park, Haekyu; Das, Nilaksh; Duggal, Rahul; Wright, Austin P.; Shaikh, Omar; Hohman, Fred; Polo Chau, Duen Horng (January 2022, IEEE Transactions on Visualization and Computer Graphics)

Full Text Available
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

https://doi.org/10.1109/VIS47514.2020.00061

Das, Nilaksh; Park, Haekyu; Wang, Zijie J.; Hohman, Fred; Firstman, Robert; Rogers, Emily; Chau, Duen Horng (October 2020, IEEE Visualization Conference (VIS))

Full Text Available
Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

https://doi.org/10.1109/TVCG.2019.2934659

Hohman, Fred; Park, Haekyu; Robinson, Caleb; Polo Chau, Duen Horng (January 2020, IEEE Transactions on Visualization and Computer Graphics)

Full Text Available
Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning

https://doi.org/10.1145/3334480.3382977

Das, Nilaksh; Park, Haekyu; Wang, Zijie J.; Hohman, Fred; Firstman, Robert; Rogers, Emily; Chau, Duen Horng (April 2020, Conference on Human Factors in Computing Systems)

Full Text Available
NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions

Park, Haekyu; Hohman, Fred; Chau, Duen Horng (April 2019, PacificVis 2019)

As deep neural networks are increasingly used in solving highstake problems, there is a pressing need to understand their internal decision mechanisms. Visualization has helped address this problem by assisting with interpreting complex deep neural networks. However, current tools often support only single data instances, or visualize layers in isolation. We present NEURALDIVERGENCE, an interactive visualization system that uses activation distributions as a high-level summary of what a model has learned. NEURALDIVERGENCE enables users to interactively summarize and compare activation distributions across layers, classes, and instances (e.g., pairs of adversarial attacked and benign images), helping them gain better understanding of neural network models.
more » « less
Full Text Available

Search for: All records