no code implementations • 29 Aug 2021 • Fahim Faisal Niloy, M. Ashraful Amin, AKM Mahbubur Rahman, Amin Ahsan Ali
Experiments on a diverse datasets verify that our method can be used to improve the classification performance of existing VAE based semi-supervised models.
no code implementations • 2 Jul 2021 • Fahim Faisal Niloy, Arif, Abu Bakar Siddik Nayem, Anis Sarker, Ovi Paul, M. Ashraful Amin, Amin Ahsan Ali, Moinul Islam Zaber, AKM Mahbubur Rahman
In this research, we have carefully accumulated a relatively challenging dataset that contains images collected from various sources for three different disasters: fire, water and land.
no code implementations • 24 Jun 2021 • Fahim Faisal Niloy, M. Ashraful Amin, Amin Ahsan Ali, AKM Mahbubur Rahman
High-resolution image segmentation remains challenging and error-prone due to the enormous size of intermediate feature maps.