Image recognition accuracy: An unseen challenge confounding today's AI | MIT News | Massachusetts Institute of Technology

A novel dataset metric, minimum viewing time (MVT), gauges image recognition complexity for AI systems by measuring the time needed for accurate human identification.

Related Keywords

David Mayo ,Alanl Yuille ,Jesse Cummings ,Xinyu Lin Meng ,Research Scientist Andrei Barbu ,Artificial Intelligence Laboratory ,Watson Ai Lab Principal Researcher Dan Gutfreund ,Principal Research Scientist Boris Katz ,Computer Science At Johns Hopkins University ,Minimum Viewing Time ,Bloomberg Distinguished Professor ,Cognitive Science ,Computer Science ,Johns Hopkins University ,Simon Kornblith Phd ,Xinyu Lin ,Scientist Andrei Barbu ,Research Scientist Boris Katz ,Principal Researcher Dan ,Neural Information Processing Systems ,Mit Csail ,Mit Center For Brains Minds And Machines ,Mit Ibm Watson Ai Lab ,Inimum Viewing Time Mvt ,Computer Vision ,Image Recognition ,Imagenet ,Bjectnet ,Bject Recognizers ,Ebiased Images ,Istribution Shift ,Ataset Difficulty Metric ,Eurips 2023 ,Vision Language Models ,Ut Of Distribution Ood Model Performance ,Adversarial Robustness ,Achine Accuracy ,Uman Psychophysics ,Neural Correlates ,Simon Kornblith ,Boris Katz ,Andrei Barbu ,Dan Gutfreund ,