User profiles for Atif Belal

Atif Belal

Student, Ecole de Technologie Superieur
Verified email at ens.etsmtl.ca
Cited by 134

Unsupervised multi-target domain adaptation through knowledge distillation

LT Nguyen-Meidine, A Belal, M Kiran… - Proceedings of the …, 2021 - openaccess.thecvf.com
Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift
between the distribution of unlabeled data from the target domain wrt labeled data from the …

Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean Teacher

A Belal, A Meethal, FP Romero… - Proceedings of the …, 2024 - openaccess.thecvf.com
Adapting visual object detectors to operational target domains is a challenging task, commonly
achieved using unsupervised domain adaptation (UDA) methods. Recent studies have …

Knowledge distillation methods for efficient unsupervised adaptation across multiple domains

A Belal, M Kiran, J Dolz, LA Blais-Morin… - Image and Vision …, 2021 - Elsevier
Beyond the complexity of CNNs that require training on large annotated datasets, the domain
shift between design and operational data has limited the adoption of CNNs in many real-…

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptive Object Detection

A Belal, A Meethal, FP Romero, M Pedersoli… - arXiv preprint arXiv …, 2024 - arxiv.org
Domain adaptation methods for object detection (OD) strive to mitigate the impact of
distribution shifts by promoting feature alignment across source and target domains. Multi-source …

Visual Modality Prompt for Adapting Vision-Language Object Detectors

HR Medeiros, A Belal, S Muralidharan… - arXiv preprint arXiv …, 2024 - arxiv.org
The zero-shot performance of object detectors degrades when tested on different modalities,
such as infrared and depth. While recent work has explored image translation techniques to …

[PDF][PDF] Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean Teacher-Supplementary Material

A Belal, A Meethal, FP Romero, M Pedersoli… - openaccess.thecvf.com
Atif Belal1, Akhil Meethal1, Francisco Perdigon Romero2, Marco Pedersoli1, Eric
Granger1 1 LIVIA, Dept. of Systems Engineering, ETS Montreal, Canada 2 GAIA Montreal …

Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

T Le Nguyen-Meidine, A Belal, M Kiran, J Dolz… - arXiv e …, 2021 - ui.adsabs.harvard.edu
Beyond the complexity of CNNs that require training on large annotated datasets, the domain
shift between design and operational data has limited the adoption of CNNs in many real-…

Phosphate-Solubilizing Bacteria as a Panacea to Alleviate Stress Effects of High Soil CaCO3 Content in Phaseolus vulgaris with Special Reference to P-Releasing …

AA Bamagoos, HF Alharby, EE Belal, AEA Khalaf… - Sustainability, 2021 - mdpi.com
The present study examines the role of leguminous compost (LC), humic acids (HA), and
phosphate-solubilizing bacteria (P-SB) in alleviating the stress effects of high soil CaCO 3 …

Alpha proteobacteria of genus Anaplasma (Rickettsiales: Anaplasmataceae): Epidemiology and characteristics of Anaplasma species related to veterinary and public …

FA Atif - Parasitology, 2016 - cambridge.org
… is also effective against horses and other ruminants (Atif et al. 2012… marginale infection in
cattle (Atif et al. 2012… marginale infection (Atif et al. 2013). Other farm management factors …

[PDF][PDF] Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

LA Blais-Morin, E Granger - researchgate.net
Beyond the complexity of CNNs that require training on large annotated datasets, the domain
shift between design and operational data has limited the adoption of CNNs in many real-…