T
Tejaswini Pedapati
Researcher at IBM
Publications - 26
Citations - 513
Tejaswini Pedapati is an academic researcher from IBM. The author has contributed to research in topics: Computer science & Exploratory data analysis. The author has an hindex of 8, co-authored 23 publications receiving 329 citations.
Papers
More filters
Posted Content
A Survey on Neural Architecture Search
TL;DR: This survey provides a formalism which unifies and categorizes the landscape of existing methods along with a detailed analysis that compares and contrasts the different approaches.
Journal ArticleDOI
Foresight: recommending visual insights
TL;DR: Foresight is introduced, a system that helps the user rapidly discover visual insights from large high-dimensional datasets by providing "global" views of insight space to help orient the user and ensure a thorough exploration process.
Patent
Model agnostic contrastive explanations for structured data
Amit Dhurandhar,Tejaswini Pedapati,Avinash Balakrishnan,Pin-Yu Chen,Karthikeyan Shanmugam,Ruchir Puri +5 more
TL;DR: This work proposes a method, Model Agnostic Contrastive Explanations Method (MACEM), to generate contrastive explanations for any classification model where one is able to only query the class probabilities for a desired input and quantitatively and qualitatively validate this approach over 5 public datasets covering diverse domains.
Posted Content
Understanding Unequal Gender Classification Accuracy from Face Images
Vidya Muthukumar,Tejaswini Pedapati,Nalini K. Ratha,Prasanna Sattigeri,Chai-Wah Wu,Brian Kingsbury,Abhishek Kumar,Samuel Thomas,Aleksandra Mojsilovic,Kush R. Varshney +9 more
TL;DR: Evidence is brought forth suggesting that differences in lip, eye and cheek structure across ethnicity lead to the differences in commercial face classification services, and lip and eye makeup are seen as strong predictors for a female face, which is a troubling propagation of a gender stereotype.
Proceedings ArticleDOI
Color-Theoretic Experiments to Understand Unequal Gender Classification Accuracy From Face Images
Vidya Muthukumar,Tejaswini Pedapati,Nalini K. Ratha,Prasanna Sattigeri,Chai-Wah Wu,Brian Kingsbury,Abhishek Kumar,Samuel Thomas,Aleksandra Mojsilovic,Kush R. Varshney +9 more
TL;DR: Initial evidence is provided that skin type alone is not the driver for the disparity in gender classification accuracy in face images, and novel stability experiments that vary an image's skin type via color-theoretic methods, namely luminance mode-shift and optimal transport are conducted.