Enregistré dans:
Détails bibliographiques
Auteurs principaux: Faber, Niels G., Ziabari, Seyed Sahand Mohammadi, Nejadasl, Fatemeh Karimi
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.18288
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929448650014720
author Faber, Niels G.
Ziabari, Seyed Sahand Mohammadi
Nejadasl, Fatemeh Karimi
author_facet Faber, Niels G.
Ziabari, Seyed Sahand Mohammadi
Nejadasl, Fatemeh Karimi
contents Multiple Object Tracking (MOT) is a computer vision task that has been employed in a variety of sectors. Some common limitations in MOT are varying object appearances, occlusions, or crowded scenes. To address these challenges, machine learning methods have been extensively deployed, leveraging large datasets, sophisticated models, and substantial computational resources. Due to practical limitations, access to the above is not always an option. However, with the recent release of foundation models by prominent AI companies, pretrained models have been trained on vast datasets and resources using state-of-the-art methods. This work tries to leverage one such foundation model, called DINOv2, through using knowledge distillation. The proposed method uses a teacher-student architecture, where DINOv2 is the teacher and the FairMOT backbone HRNetv2 W18 is the student. The results imply that although the proposed method shows improvements in certain scenarios, it does not consistently outperform the original FairMOT model. These findings highlight the potential and limitations of applying foundation models in knowledge
format Preprint
id arxiv_https___arxiv_org_abs_2407_18288
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT
Faber, Niels G.
Ziabari, Seyed Sahand Mohammadi
Nejadasl, Fatemeh Karimi
Computer Vision and Pattern Recognition
Multiple Object Tracking (MOT) is a computer vision task that has been employed in a variety of sectors. Some common limitations in MOT are varying object appearances, occlusions, or crowded scenes. To address these challenges, machine learning methods have been extensively deployed, leveraging large datasets, sophisticated models, and substantial computational resources. Due to practical limitations, access to the above is not always an option. However, with the recent release of foundation models by prominent AI companies, pretrained models have been trained on vast datasets and resources using state-of-the-art methods. This work tries to leverage one such foundation model, called DINOv2, through using knowledge distillation. The proposed method uses a teacher-student architecture, where DINOv2 is the teacher and the FairMOT backbone HRNetv2 W18 is the student. The results imply that although the proposed method shows improvements in certain scenarios, it does not consistently outperform the original FairMOT model. These findings highlight the potential and limitations of applying foundation models in knowledge
title Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.18288