Search Results for author: Mehrdad Noori

Found 5 papers, 4 papers with code

TFS-ViT: Token-Level Feature Stylization for Domain Generalization

1 code implementation28 Mar 2023 Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A. Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers

This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains.

Domain Generalization

TTTFlow: Unsupervised Test-Time Training with Normalizing Flow

1 code implementation20 Oct 2022 David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers

A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time.

Image Classification

Attention-Guided Version of 2D UNet for Automatic Brain Tumor Segmentation

no code implementations4 Apr 2020 Mehrdad Noori, Ali Bahri, Karim Mohammadi

Most of the existing methods, especially UNet-based networks, integrate low-level and high-level features in a naive way, which may result in confusion for the model.

Brain Tumor Segmentation Tumor Segmentation

DFNet: Discriminative feature extraction and integration network for salient object detection

1 code implementation3 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.

object-detection RGB Salient Object Detection +2

CAGNet: Content-Aware Guidance for Salient Object Detection

3 code implementations29 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.

object-detection RGB Salient Object Detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.