3 papers
cs.LG2024
Model Debiasing by Learnable Data Augmentation
Pietro Morerio, Ruggero Ragonesi, Vittorio Murino
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual ta…
cs.CV2020
Learning Unbiased Representations via Mutual Information Backpropagation
Ruggero Ragonesi, Riccardo Volpi, Jacopo Cavazza +1
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attribut…
cs.CV2020
Generative Pseudo-label Refinement for Unsupervised Domain Adaptation
Pietro Morerio, Riccardo Volpi, Ruggero Ragonesi +1
We investigate and characterize the inherent resilience of conditional Generative Adversarial Networks (cGANs) against noise in their conditioning labels, and exploit this fact in…