Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

NeuroMapper: In-browser Visualizer for Neural Network Training


Oct 22, 2022
Zhiyan Zhou, Kevin Li, Haekyu Park, Megan Dass, Austin Wright, Nilaksh Das, Duen Horng Chau

Add code

* IEEE VIS 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning


Apr 05, 2022
Nilaksh Das, Duen Horng Chau

Add code

* Submitted to Insterspeech 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning


Apr 02, 2022
Nilaksh Das, Sheng-Yun Peng, Duen Horng Chau

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ConceptEvo: Interpreting Concept Evolution in Deep Learning Training


Mar 30, 2022
Haekyu Park, Seongmin Lee, Benjamin Hoover, Austin Wright, Omar Shaikh, Rahul Duggal, Nilaksh Das, Judy Hoffman, Duen Horng Chau

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


Aug 29, 2021
Haekyu Park, Nilaksh Das, Rahul Duggal, Austin P. Wright, Omar Shaikh, Fred Hohman, Duen Horng Chau

Add code

* Accepted to IEEE VIS'21 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

EnergyVis: Interactively Tracking and Exploring Energy Consumption for ML Models


Mar 30, 2021
Omar Shaikh, Jon Saad-Falcon, Austin P Wright, Nilaksh Das, Scott Freitas, Omar Isaac Asensio, Duen Horng Chau

Add code

* 7 pages, 5 figures; CHI 2021 Extended Abstracts 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning


Mar 10, 2021
Nilaksh Das, Sravan Bodapati, Monica Sunkara, Sundararajan Srinivasan, Duen Horng Chau

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


Jan 26, 2021
Haekyu Park, Zijie J. Wang, Nilaksh Das, Anindya S. Paul, Pruthvi Perumalla, Zhiyan Zhou, Duen Horng Chau

Add code

* Accepted at AAAI'21 Demo 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks


Sep 08, 2020
Nilaksh Das, Haekyu Park, Zijie J. Wang, Fred Hohman, Robert Firstman, Emily Rogers, Duen Horng Chau

Add code

* This paper is accepted at IEEE VIS'20 Short Paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization


May 01, 2020
Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, Duen Horng Chau

Add code

* 11 pages, 14 figures. For a demo video, see https://youtu.be/HnWIHWFbuUQ For a live demo, visit https://poloclub.github.io/cnn-explainer/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>