Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Araghi, HamidReza Yaghoubi"'
Autor:
Noohdani, Fahimeh Hosseini, Hosseini, Parsa, Parast, Aryan Yazdan, Araghi, Hamidreza Yaghoubi, Baghshah, Mahdieh Soleymani
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
While standard Empirical Risk Minimization (ERM) training is proven effective for image classification on in-distribution data, it fails to perform well on out-of-distribution samples. One of the main sources of distribution shift for image classific
Externí odkaz:
http://arxiv.org/abs/2402.18919
Autor:
Ghaznavi, Mahdi, Asadollahzadeh, Hesam, Araghi, HamidReza Yaghoubi, Noohdani, Fahimeh Hosseini, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani
It is well-known that training neural networks for image classification with empirical risk minimization (ERM) makes them vulnerable to relying on spurious attributes instead of causal ones for prediction. Previously, deep feature re-weighting (DFR)
Externí odkaz:
http://arxiv.org/abs/2312.04893