5 papers · 1 filter
Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
Xuan Qi, Yi Wei, Fanqi Yu +3
Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We stud…
Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing
Massimiliano Ciranni, Vito Paolo Pastore, Roberto Di Via +3
Deep learning model effectiveness in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlation…
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…
Say My Name: a Model's Bias Discovery Framework
Massimiliano Ciranni, Luca Molinaro, Carlo Alberto Barbano +4
In the last few years, due to the broad applicability of deep learning to downstream tasks and end-to-end training capabilities, increasingly more concerns about potential biases t…
Looking at Model Debiasing through the Lens of Anomaly Detection
Vito Paolo Pastore, Massimiliano Ciranni, Davide Marinelli +2
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between…