Search Results for author: Mohsen Ali

Found 23 papers, 7 papers with code

Towards Improving Calibration in Object Detection Under Domain Shift

no code implementations15 Sep 2022 Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali

To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD).

Decision Making object-detection +1

Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation

no code implementations20 Jun 2022 Javed Iqbal, Hamza Rawal, Rehan Hafiz, Yu-Tseh Chi, Mohsen Ali

Due to the domain shift, this decision boundary is unaligned in the target domain, resulting in noisy pseudo labels adversely affecting self-supervised domain adaptation.

Disentanglement Domain Adaptation +4

Mapping Temporary Slums from Satellite Imagery using a Semi-Supervised Approach

no code implementations9 Apr 2022 M. Fasi ur Rehman, Izza Ali, Waqas Sultani, Mohsen Ali

A small set of seed samples (32 in our case) are automatically discovered by analyzing the temporal changes, which are manually labeled to train a segmentation and representation learning module.

Representation Learning Semi-Supervised Semantic Segmentation

FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images

no code implementations7 Jan 2022 Javed Iqbal, Rehan Hafiz, Mohsen Ali

We propose a self-entropy and multi-scale information augmented self-supervised domain adaptation method (FogAdapt) to minimize the domain shift in foggy scenes segmentation.

Domain Adaptation Foggy Scene Segmentation +1

SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

no code implementations NeurIPS 2021 Muhammad Akhtar Munir, Muhammad Haris Khan, M. Sarfraz, Mohsen Ali

In this paper, we propose to leverage model’s predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.

object-detection Object Detection

Towards Low-Cost and Efficient Malaria Detection

no code implementations CVPR 2022 Waqas Sultani, Wajahat Nawaz, Syed Javed, Muhammad Sohail Danish, Asma Saadia, Mohsen Ali

We design a mechanism to transfer these annotations from the high-cost microscope at high magnification to the low-cost microscope, at multiple magnifications.

Domain Adaptation

Out of distribution detection for skin and malaria images

no code implementations2 Nov 2021 Muhammad Zaida, Shafaqat Ali, Mohsen Ali, Sarfaraz Hussein, Asma Saadia, Waqas Sultani

Deep neural networks have shown promising results in disease detection and classification using medical image data.

Metric Learning OOD Detection +1

Cross-Region Building Counting in Satellite Imagery using Counting Consistency

no code implementations26 Oct 2021 Muaaz Zakria, Hamza Rawal, Waqas Sultani, Mohsen Ali

We then exploit counting consistency constraints, within-image count consistency, and across-image count consistency, to decrease the domain shift.

Management Unsupervised Domain Adaptation

Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

no code implementations1 Oct 2021 Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali

In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.

object-detection Object Detection

A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images

no code implementations17 Feb 2021 Qazi Ammar Arshad, Mohsen Ali, Saeed-Ul Hassan, Chen Chen, Ayisha Imran, Ghulam Rasul, Waqas Sultani

Malaria microscopy, microscopic examination of stained blood slides to detect parasite Plasmodium, is considered to be a gold-standard for detecting life-threatening disease malaria.

General Classification

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

1 code implementation ECCV 2020 M. Naseer Subhani, Mohsen Ali

Specifically, we show that semantic segmentation model produces output with high entropy when presented with scaled-up patches of target domain, in comparison to when presented original size images.

Self-Supervised Learning Semantic Segmentation +2

Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite Imagery

1 code implementation5 Jul 2020 Javed Iqbal, Mohsen Ali

We thoroughly study the limitations of existing domain adaptation methods and propose a weakly-supervised adaptation strategy where we assume image-level labels are available for the target domain.

Image Classification Unsupervised Domain Adaptation

Localizing Firearm Carriers by Identifying Human-Object Pairs

no code implementations19 May 2020 Abdul Basit, Muhammad Akhtar Munir, Mohsen Ali, Arif Mahmood

Visual identification of gunmen in a crowd is a challenging problem, that requires resolving the association of a person with an object (firearm).

Association Human-Object Interaction Detection

MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling

2 code implementations30 Sep 2019 Javed Iqbal, Mohsen Ali

Thus helping latent space learn the representation even when there are very few pixels belonging to the domain category (small object for example) compared to rest of the image.

Domain Adaptation Self-Supervised Learning +2

Twin-Net Descriptor: Twin Negative Mining With Quad Loss for Patch-Based Matching

no code implementations IEEE Access 2019 Aman Irshad, Rehan Hafiz, Mohsen Ali, Muhammad Faisal, Yongju Cho, Jeongil Seo

Our results on Brown and HPatches datasets demonstrate Twin-Net's consistently better performance as well as better discriminatory and generalization capability as compared to the state-of-art.

Patch Matching

Leveraging Orientation for Weakly Supervised Object Detection with Application to Firearm Localization

1 code implementation22 Apr 2019 Javed Iqbal, Muhammad Akhtar Munir, Arif Mahmood, Afsheen Rafaqat Ali, Mohsen Ali

The OAOD algorithm is evaluated on the ITUF dataset and compared with current state-of-the-art object detectors, including fully supervised oriented object detectors.

object-detection Weakly Supervised Object Detection

Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting

no code implementations1 Apr 2019 Anza Shakeel, Waqas Sultani, Mohsen Ali

In this paper, we attempt to address the challenging problem of counting built-structures in the satellite imagery.

Automatic Image Transformation for Inducing Affect

1 code implementation25 Jul 2017 Afsheen Rafaqat Ali, Mohsen Ali

In this paper we present an automatic image-transformation method that transforms the source image such that it can induce an emotional affect on the viewer, as desired by the user.

Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities

no code implementations12 May 2017 Anza Shakeel, Mohsen Ali

Deep convolutional neural networks (CNNs) have outperformed existing object recognition and detection algorithms.

Object Recognition

High-Level Concepts for Affective Understanding of Images

no code implementations8 May 2017 Afsheen Rafaqat Ali, Usman Shahid, Mohsen Ali, Jeffrey Ho

This paper aims to bridge the affective gap between image content and the emotional response of the viewer it elicits by using High-Level Concepts (HLCs).


Block and Group Regularized Sparse Modeling for Dictionary Learning

no code implementations CVPR 2013 Yu-Tseh Chi, Mohsen Ali, Ajit Rajwade, Jeffrey Ho

This paper proposes a dictionary learning framework that combines the proposed block/group (BGSC) or reconstructed block/group (R-BGSC) sparse coding schemes with the novel Intra-block Coherence Suppression Dictionary Learning (ICS-DL) algorithm.

Dictionary Learning

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