Search Results for author:
Found 14 papers, 5 papers with code
Towards Reliable Dermatology Evaluation Benchmarks
Benchmark datasets for digital dermatology unwittingly contain inaccuracies that reduce trust in model performance estimates.
Augmenting medical image classifiers with synthetic data from latent diffusion models
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.
Art and the science of generative AI: A deeper dive
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.
SelfClean: A Self-Supervised Data Cleaning Strategy
Most benchmark datasets for computer vision contain irrelevant images, near duplicates, and label errors.
Improving dermatology classifiers across populations using images generated by large diffusion models
Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations.
Computational Empathy Counteracts the Negative Effects of Anger on Creative Problem Solving
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.
Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm
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.
Identifying the Context Shift between Test Benchmarks and Production Data
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.
Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video
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.
Social influence leads to the formation of diverse local trends
How does the visual design of digital platforms impact user behavior and the resulting environment?
Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds
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?
Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset
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.
Human detection of machine manipulated media
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.
Closing the AI Knowledge Gap
AI researchers employ not only the scientific method, but also methodology from mathematics and engineering.
