Advances in machine learning for health care have brought concerns about bias from the research community; specifically, the introduction, perpetuation, or exacerbation of care …
Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts. However, the lack of consistent settings and …
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding" spurious" …
Machine learning systems are known to be sensitive to spurious correlations between biased features of the inputs (eg, background, texture, and secondary objects) and the …
Y Liu, B Guo, N Li, Y Ding, Z Zhang… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The fundamental goal of …
Web-based content analysis tasks, such as labeling toxicity, misinformation, or spam often rely on machine learning models to achieve cost and scale efficiencies. As these models …
We consider the problem of estimating the mean of a random variable Y subject to non- ignorable missingness, ie, where the missingness mechanism depends on Y. We connect …
Deep neural networks (DNNs) have exhibited remarkable performance across various tasks, yet their susceptibility to spurious correlations poses a significant challenge for out-of …
I Mason, A Sarkar, T Sasaki, X Boix - arXiv preprint arXiv:2306.09005, 2023 - arxiv.org
By default neural networks are not robust to changes in data distribution. This has been demonstrated with simple image corruptions, such as blurring or adding noise, degrading …