Výsledky vyhledávání - "Stone, Rebecca"

Report

Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task

Autor: Stone, Rebecca S., Chavarrias-Solano, Pedro E., Bulpitt, Andrew J., Hogg, David C., Ali, Sharib

While several previous studies have devised methods for segmentation of polyps, most of these methods are not rigorously assessed on multi-center datasets. Variability due to appearance of polyps from one center to another, difference in endoscopic i

Externí odkaz: http://arxiv.org/abs/2309.06807

Zobrazit plný text záznamu

Report

Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network

Autor: Stone, Rebecca S, Ravikumar, Nishant, Bulpitt, Andrew J, Hogg, David C

The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual datasets. Due to the difficulty and variability of the task, no single d

Externí odkaz: http://arxiv.org/abs/2303.16564

Zobrazit plný text záznamu

Kniha

The jaguar within [elektronicky zdroj] : shamanic trance in ancient Central and South American art / Rebecca R. Stone.

Autor: Stone, Rebecca, 1958-

Externí odkaz: Kolekce e-knih KNAV

Report

Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation

Autor: Stone, Rebecca S, Ravikumar, Nishant, Bulpitt, Andrew J, Hogg, David C

Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to mitigate. We

Externí odkaz: http://arxiv.org/abs/2204.09389

Zobrazit plný text záznamu