Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation von Noohdani, Fahimeh Hosseini, Hosseini, Parsa, Parast, Aryan Yazdan, Araghi, Hamidreza Yaghoubi, Baghshah, Mahdieh Soleymani

Volltext bestellen

Annotation-Free Group Robustness via Loss-Based Resampling von Ghaznavi, Mahdi, Asadollahzadeh, Hesam, Araghi, HamidReza Yaghoubi, Noohdani, Fahimeh Hosseini, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani

Volltext bestellen

Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation von Ghaznavi, Mahdi, Asadollahzadeh, Hesam, Noohdani, Fahimeh Hosseini, Tabar, Soroush Vafaie, Hasani, Hosein, Alvanagh, Taha Akbari, Rohban, Mohammad Hossein, Baghshah, Mahdieh Soleymani

Volltext bestellen

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation von Fahimeh Hosseini Noohdani, Hosseini, Parsa, Aryan Yazdan Parast, Hamidreza Yaghoubi Araghi, Mahdieh Soleymani Baghshah

Volltext

Annotation-Free Group Robustness via Loss-Based Resampling von Ghaznavi, Mahdi, Asadollahzadeh, Hesam, HamidReza Yaghoubi Araghi, Fahimeh Hosseini Noohdani, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah

Volltext

Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation von Ghaznavi, Mahdi, Asadollahzadeh, Hesam, Fahimeh Hosseini Noohdani, Soroush Vafaie Tabar, Hasani, Hosein, Taha Akbari Alvanagh, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah

Volltext