Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning

no code implementations • 27 Jul 2021 • Reece Walsh, Mohamed H. Abdelpakey, Mohamed S. Shehata, Mostafa M. Mohamed

The selected techniques are trained on a non-medical dataset and then tested on two out-of-domain, human cell datasets.

Classification Few-Shot Learning +1

NullSpaceNet: Nullspace Convoluional Neural Network with Differentiable Loss Function

no code implementations • 25 Apr 2020 • Mohamed H. Abdelpakey, Mohamed S. Shehata

We propose NullSpaceNet, a novel network that maps from the pixel level input to a joint-nullspace (as opposed to the traditional feature space), where the newly learned joint-nullspace features have clearer interpretation and are more separable.

DomainSiam: Domain-Aware Siamese Network for Visual Object Tracking

no code implementations • 21 Aug 2019 • Mohamed H. Abdelpakey, Mohamed S. Shehata

Recently, Siamese trackers have achieved state-of-the-art performance on recent benchmarks.

Image Classification Object +2

DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking

1 code implementation • 7 Sep 2018 • Mohamed H. Abdelpakey, Mohamed S. Shehata, Mostafa M. Mohamed

Convolutional Siamese neural networks have been recently used to track objects using deep features.

Object Tracking