Deepta Rajan — accepted AI-conference papers

2021

Designing Counterfactual Generators using Deep Model Inversion

Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Deepta Rajan, Jia Liang, Akshay Chaudhari, Andreas Spanias

NeurIPS 2021poster

Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models. Commonly referred to as counterfactuals, the synthesized explanations are required to contain discernib…

Cited by 27 Source ↗PDF ↗Scholar ↗

2021

Fair Selective Classification Via Sufficiency

Joshua K Lee, Yuheng Bu, Deepta Rajan, Prasanna Sattigeri, Rameswar Panda, Subhro Das +1

ICML 2021oral

Selective classification is a powerful tool for decision-making in scenarios where mistakes are costly but abstentions are allowed. In general, by allowing a classifier to abstain, one can improve the performance of a model at the cost of reducing coverage and classifying fewer samples. However, rec…

Cited by 33 Source ↗PDF ↗code ↗Scholar ↗

2020

Learn-By-Calibrating: Using Calibration As A Training Objective

Jayaraman J. Thiagarajan, Bindya Venkatesh, Deepta Rajan

ICASSP 2020accepted

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar t…

Cited by 0 Source ↗Scholar ↗