Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Mozafari, Azadeh Sadat"'
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have been proposed to improve the pre
Externí odkaz:
http://arxiv.org/abs/1911.11195
The great performances of deep learning are undeniable, with impressive results over a wide range of tasks. However, the output confidence of these models is usually not well-calibrated, which can be an issue for applications where confidence on the
Externí odkaz:
http://arxiv.org/abs/1905.00174
Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of
Externí odkaz:
http://arxiv.org/abs/1810.11586
Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes int
Externí odkaz:
http://arxiv.org/abs/1808.08282
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly calibrated for
Externí odkaz:
http://arxiv.org/abs/1802.07881
Autor:
Mozafari, Azadeh Sadat *, Jamzad, Mansour
Publikováno v:
In Computer Vision and Image Understanding September 2017 162:116-134
Publikováno v:
In Pattern Recognition August 2016 56:142-158
Publikováno v:
2014 IEEE International Conference on Image Processing (ICIP); 2014, p4077-4081, 5p