1 code implementation • 13 Sep 2023 • Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Matthew Groh, Roxana Daneshjou, Labelling Consortium, Alexander A. Navarini, Marc Pouly
Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates.
no code implementations • 23 Aug 2023 • Luke W. Sagers, James A. Diao, Luke Melas-Kyriazi, Matthew Groh, Pranav Rajpurkar, Adewole S. Adamson, Veronica Rotemberg, Roxana Daneshjou, Arjun K. Manrai
While hundreds of artificial intelligence (AI) algorithms are now approved or cleared by the US Food and Drugs Administration (FDA), many studies have shown inconsistent generalization or latent bias, particularly for underrepresented populations.
no code implementations • 7 Jun 2023 • Ziv Epstein, Aaron Hertzmann, Laura Herman, Robert Mahari, Morgan R. Frank, Matthew Groh, Hope Schroeder, Amy Smith, Memo Akten, Jessica Fjeld, Hany Farid, Neil Leach, Alex Pentland, Olga Russakovsky
A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation.
no code implementations • 26 May 2023 • Fabian Gröger, Simone Lionetti, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Ludovic Amruthalingam, Labelling Consortium, Matthew Groh, Alexander A. Navarini, Marc Pouly
Most benchmark datasets for computer vision contain irrelevant images, near duplicates, and label errors.
no code implementations • 23 Nov 2022 • Luke W. Sagers, James A. Diao, Matthew Groh, Pranav Rajpurkar, Adewole S. Adamson, Arjun K. Manrai
Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations.
1 code implementation • 15 Aug 2022 • Matthew Groh, Craig Ferguson, Robert Lewis, Rosalind Picard
In an online experiment with 1, 006 participants randomly assigned to an emotion elicitation intervention (with a control elicitation condition and anger elicitation condition) and a computational empathy intervention (with a control virtual agent and an empathic virtual agent), we examine how anger and empathy influence participants' performance in solving a word game based on Wordle.
1 code implementation • 6 Jul 2022 • Matthew Groh, Caleb Harris, Roxana Daneshjou, Omar Badri, Arash Koochek
As a start towards increasing transparency, AI researchers have appropriated the use of the Fitzpatrick skin type (FST) from a measure of patient photosensitivity to a measure for estimating skin tone in algorithmic audits of computer vision applications including facial recognition and dermatology diagnosis.
no code implementations • 3 Jul 2022 • Matthew Groh
Moreover, we identify three methods for addressing context shift that would otherwise lead to model prediction errors: first, we describe how human intuition and expert knowledge can identify semantically meaningful features upon which models systematically fail, second, we detail how dynamic benchmarking - with its focus on capturing the data generation process - can promote generalizability through corroboration, and third, we highlight that clarifying a model's limitations can reduce unexpected errors.
no code implementations • 25 Feb 2022 • Matthew Groh, Aruna Sankaranarayanan, Nikhil Singh, Dong Young Kim, Andrew Lippman, Rosalind Picard
Recent advances in technology for hyper-realistic visual and audio effects provoke the concern that deepfake videos of political speeches will soon be indistinguishable from authentic video recordings.
no code implementations • 17 Aug 2021 • Ziv Epstein, Matthew Groh, Abhimanyu Dubey, Alex "Sandy" Pentland
How does the visual design of digital platforms impact user behavior and the resulting environment?
1 code implementation • 13 May 2021 • Matthew Groh, Ziv Epstein, Chaz Firestone, Rosalind Picard
The recent emergence of machine-manipulated media raises an important societal question: how can we know if a video that we watch is real or fake?
2 code implementations • 20 Apr 2021 • Matthew Groh, Caleb Harris, Luis Soenksen, Felix Lau, Rachel Han, Aerin Kim, Arash Koochek, Omar Badri
We train a deep neural network model to classify 114 skin conditions and find that the model is most accurate on skin types similar to those it was trained on.
no code implementations • 6 Jul 2019 • Matthew Groh, Ziv Epstein, Nick Obradovich, Manuel Cebrian, Iyad Rahwan
Here we report on a randomized experiment designed to study the effect of exposure to media manipulations on over 15, 000 individuals' ability to discern machine-manipulated media.
no code implementations • 20 Mar 2018 • Ziv Epstein, Blakeley H. Payne, Judy Hanwen Shen, Abhimanyu Dubey, Bjarke Felbo, Matthew Groh, Nick Obradovich, Manuel Cebrian, Iyad Rahwan
AI researchers employ not only the scientific method, but also methodology from mathematics and engineering.