4 papers
Remedying uncertainty representations in visual inference through Explaining-Away Variational Autoencoders
Josefina Catoni, Domonkos Martos, Ferenc Csikor +5
Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), hav…
CheXmask-U: Quantifying uncertainty in landmark-based anatomical segmentation for X-ray images
Matias Cosarinsky, Nicolas Gaggion, Rodrigo Echeveste +1
In this work, we study uncertainty estimation for anatomical landmark-based segmentation on chest X-rays. Inspired by hybrid neural network architectures that combine standard imag…
BM-CL: Bias Mitigation through the lens of Continual Learning
Lucas Mansilla, Rodrigo Echeveste, Camila Gonzalez +2
Biases in machine learning pose significant challenges, particularly when models amplify disparities that affect disadvantaged groups. Traditional bias mitigation techniques often…
Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation
Estanislao Claucich, Sara Hooker, Diego H. Milone +2
Ensembling is commonly regarded as an effective way to improve the general performance of models in machine learning, while also increasing the robustness of predictions. When it c…