activity
20172023
most citedEvaluating Visual Conversational Agents via Cooperative Human-AI Games

38 citations · 79 across the 5 of their papers we have counts for

collaborators

10 papers

cs.CV202326 cited

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Micah Goldblum, Hossein Souri, Renkun Ni +10

Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an…

cs.CV2022

Can domain adaptation make object recognition work for everyone?

Viraj Prabhu, Ramprasaath R. Selvaraju, Judy Hoffman +1

Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperf…

cs.CV20215 cited

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…

cs.CV2020

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

Viraj Prabhu, Shivam Khare, Deeksha Kartik +1

Many existing approaches for unsupervised domain adaptation (UDA) focus on adapting under only data distribution shift and offer limited success under additional cross-domain label…

cs.CV2020

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings

Viraj Prabhu, Arjun Chandrasekaran, Kate Saenko +1

Generalizing deep neural networks to new target domains is critical to their real-world utility. In practice, it may be feasible to get some target data labeled, but to be cost-eff…

cs.LG201910 cited

Open Set Medical Diagnosis

Viraj Prabhu, Anitha Kannan, Geoffrey J. Tso +4

Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they ha…