Object Detection with Transformers: A Review
Sensors · 01.10.2025 · 25 (19) · 6025
DOI: 10.3390/s25196025 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 01.10.2025. Verfasst von Tahira Shehzadi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany. Die Arbeit wurde bisher 82-mal zitiert (Crossref) und nennt 228 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European project AIRISE.
Abstract (Originalsprache)
The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks. A detection transformer (DETR) introduces transformers to object detection tasks by reframing detection as a set prediction problem. Consequently, it eliminates the need for proposal generation and post-processing steps. Despite competitive performance, DETR initially suffered from slow convergence and poor detection of small objects. However, numerous improvements are proposed to address these issues, leading to substantial improvements, enabling DETR to achieve state-of-the-art performance. To the best of our knowledge, this paper is the first to provide a comprehensive review of 25 recent DETR advancements. We dive into both the foundational modules of DETR and its recent enhancements, such as modifications to the backbone structure, query design strategies, and refinements to attention mechanisms. Moreover, we conduct a comparative analysis across various detection transformers, evaluating their performance and network architectures. We aim for this study to encourage further research in addressing the existing challenges and exploring the application of transformers in the object detection domain.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany.
- Mindgarage Lab, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany.
- German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany.
- Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 971 87 Luleå, Sweden.
ORCID-Profile: Tahira Shehzadi, Khurram Azeem Hashmi, Marcus Liwicki, Muhammad Zeshan Afzal
Förderung
- European project AIRISE
Zitieren
APA
Shehzadi, T., Hashmi, K. A., Liwicki, M., Stricker, D., & Afzal, M. Z. (2025). Object Detection with Transformers: A Review. Sensors, 25(19), 6025. https://doi.org/10.3390/s25196025
Vancouver
Shehzadi T, Hashmi KA, Liwicki M, Stricker D, Afzal MZ. Object Detection with Transformers: A Review. Sensors. 2025;25(19):6025. doi:10.3390/s25196025
BibTeX
@article{Shehzadi2025,
author = {Shehzadi, Tahira and Hashmi, Khurram Azeem and Liwicki, Marcus and Stricker, Didier and Afzal, Muhammad Zeshan},
title = {Object Detection with Transformers: A Review},
journal = {Sensors},
year = {2025},
volume = {25},
number = {19},
pages = {6025},
doi = {10.3390/s25196025}
}
EUVIMED