2 papers
cs.AI2024
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…
cs.LG2021
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks
Guoxuan Xia, Sangwon Ha, Tiago Azevedo +1
Modern convolutional neural networks (CNNs) are known to be overconfident in terms of their calibration on unseen input data. That is to say, they are more confident than they are…