4 papers
Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
Firas Gabetni, Giuseppe Curci, Andrea Pilzer +3
Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, the…
Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
Adrien Lafage, Olivier Laurent, Firas Gabetni +1
Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle…
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
Guoxuan Xia, Olivier Laurent, Gianni Franchi +1
Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ``Hard'' one-hot labe…
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
Gianni Franchi, Dat Nguyen Trong, Nacim Belkhir +2
Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. In this paper, we are the first to…