activity
20192021
most citedOn the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

76 citations · 86 across the 4 of their papers we have counts for

collaborators

6 papers

eess.IV20211 cited

Detecting Spurious Correlations with Sanity Tests for Artificial Intelligence Guided Radiology Systems

Usman Mahmood, Robik Shrestha, David D. B. Bates +4

Artificial intelligence (AI) has been successful at solving numerous problems in machine perception. In radiology, AI systems are rapidly evolving and show progress in guiding trea…

cs.CV202076 cited

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Damien Teney, Kushal Kafle, Robik Shrestha +3

Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set. OOD benchmarks are d…

cs.LG2019

REMIND Your Neural Network to Prevent Catastrophic Forgetting

Tyler L. Hayes, Kushal Kafle, Robik Shrestha +2

People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the…

cs.CV2019

Answering Questions about Data Visualizations using Efficient Bimodal Fusion

Kushal Kafle, Robik Shrestha, Brian Price +2

Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie cha…

cs.LG20193 cited

Challenges and Prospects in Vision and Language Research

Kushal Kafle, Robik Shrestha, Christopher Kanan

Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of…

cs.CV20196 cited

Answer Them All! Toward Universal Visual Question Answering Models

Robik Shrestha, Kushal Kafle, Christopher Kanan

Visual Question Answering (VQA) research is split into two camps: the first focuses on VQA datasets that require natural image understanding and the second focuses on synthetic dat…