no code implementations • 31 May 2022 • Fereshteh Shakeri, Malik Boudiaf, Sina Mohammadi, Ivaxi Sheth, Mohammad Havaei, Ismail Ben Ayed, Samira Ebrahimi Kahou
We build few-shot tasks and base-training data with various tissue types, different levels of domain shifts stemming from various cancer sites, and different class-granularity levels, thereby reflecting realistic scenarios.
1 code implementation • 15 Feb 2021 • Sina Mohammadi, Mariana Belgiu, Alfred Stein
We conclude that using the IOU loss function provides a superior choice to learn individual crop types.
1 code implementation • 3 Apr 2020 • Mehrdad Noori, Sina Mohammadi, Sina Ghofrani Majelan, Ali Bahri, Mohammad Havaei
To address the second challenge, we propose an Attention-based Multi-level Integrator Module to give the model the ability to assign different weights to multi-level feature maps.
no code implementations • 22 Mar 2020 • Sina Mohammadi, Sina Ghofrani Majelan, Shahriar B. Shokouhi
A big challenge in action recognition in still images is the lack of large enough datasets, which is problematic for training deep Convolutional Neural Networks (CNNs) due to the overfitting issue.
3 code implementations • 29 Nov 2019 • Sina Mohammadi, Mehrdad Noori, Ali Bahri, Sina Ghofrani Majelan, Mohammad Havaei
Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results.