5 citations · 8 across the 3 of their papers we have counts for
3 papers
ICON: Reliably Benchmarking Predictive Inequity in Object Detection
Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky +1
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising. Ana…
Mitigating Bias in Visual Transformers via Targeted Alignment
Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar +1
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness…
UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar +1
Deep learning models have been shown to learn spurious correlations from data that sometimes lead to systematic failures for certain subpopulations. Prior work has typically diagno…