activity
20242026
collaborators

5 papers

cs.CV2026

VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation

Xuan Qi, Daniele Berardini, Dario Serez +2

Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shift. Recent diffusion-based UD…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…