1 code implementation • 24 Jun 2019 • Muhammad Rehman Zafar, Naimul Mefraz Khan
While LIME and similar local algorithms have gained popularity due to their simplicity, the random perturbation and feature selection methods result in "instability" in the generated explanations, where for the same prediction, different explanations can be generated.
2 code implementations • 4 Jun 2019 • Naimul Mefraz Khan, Marcia Hon, Nabila Abraham
In this paper, we attempt solving these issues with transfer learning, where the state-of-the-art VGG architecture is initialized with pre-trained weights from large benchmark datasets consisting of natural images.
no code implementations • 13 Feb 2019 • Naimul Mefraz Khan, Nabila Abraham, Ling Guan
In this paper, we highlight three issues that limit performance of machine learning on biomedical images, and tackle them through 3 case studies: 1) Interactive Machine Learning (IML): we show how IML can drastically improve exploration time and quality of direct volume rendering.
1 code implementation • 23 Jan 2019 • Nairouz Mrabah, Naimul Mefraz Khan, Riadh Ksantini, Zied Lachiri
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities.
Ranked #1 on Image Clustering on MNIST-test
6 code implementations • 18 Oct 2018 • Nabila Abraham, Naimul Mefraz Khan
We propose a generalized focal loss function based on the Tversky index to address the issue of data imbalance in medical image segmentation.
Ranked #1 on Lesion Segmentation on BUS 2017 Dataset B