Discovering and Mitigating Visual Biases through Keyword Explanation
Addressing biases in computer vision models is crucial for real-world AI deployments.
However mitigating visual biases is challenging due to their unexplainable nature often …
However mitigating visual biases is challenging due to their unexplainable nature often …
Angler: Helping machine translation practitioners prioritize model improvements
Machine learning (ML) models can fail in unexpected ways in the real world, but not all
model failures are equal. With finite time and resources, ML practitioners are forced to …
model failures are equal. With finite time and resources, ML practitioners are forced to …
Variation of Gender Biases in Visual Recognition Models Before and After Finetuning
We introduce a framework to measure how biases change before and after fine-tuning a
large scale visual recognition model for a downstream task. Deep learning models trained …
large scale visual recognition model for a downstream task. Deep learning models trained …
Reducing bias in AI-based analysis of visual artworks
Empirical research in science and the humanities is vulnerable to bias which, by definition,
implies incorrect or misleading findings. Artificial intelligence-based analysis of visual …
implies incorrect or misleading findings. Artificial intelligence-based analysis of visual …
Interactive Visual Feature Search
D Ulrich, R Fong - arXiv preprint arXiv:2211.15060, 2022 - arxiv.org
Many visualization techniques have been created to help explain the behavior of
convolutional neural networks (CNNs), but they largely consist of static diagrams that convey …
convolutional neural networks (CNNs), but they largely consist of static diagrams that convey …
Designing for Reliability in Algorithmic Systems
SB Robertson - 2023 - escholarship.org
As we introduce complex algorithmic systems into decision-making in high-stakes domains,
system designers need principled approaches to help people set their expectations of these …
system designers need principled approaches to help people set their expectations of these …
[PDF][PDF] Reducing Bias in AI-based Analysis of Visual Artworks
E Mansfield, J Russell, C Adams - infolab.stanford.edu
Empirical research in science and the humanities is vulnerable to bias which, by definition,
implies incorrect or misleading findings. Artificial intelligence-based analysis of visual …
implies incorrect or misleading findings. Artificial intelligence-based analysis of visual …