CoChat
Cited by 59

The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.

Advancements in Small-Object Detection (2023–2025): Approaches, Datasets, Benchmarks, Applications, and Practical Guidance

Aldubaikhi, Ali, Patel, Sarosh · 2025 · Applied Sciences

Abstract

Small-object detection (SOD) remains an important and growing challenge in computer vision and is the backbone of many applications, including autonomous vehicles, aerial surveillance, medical imaging, and industrial quality control. Small objects, in pixels, lose discriminative features during deep neural network processing, making them difficult to disentangle from background noise and other artifacts. This survey presents a comprehensive and systematic review of the SOD advancements between 2023 and 2025, a period marked by the maturation of transformer-based architectures and a return to efficient, realistic deployment. We applied the PRISMA methodology for this work, yielding 112 seminal works in the field to ensure the robustness of our foundation for this study. We present a critical taxonomy of the developments since 2023, arranged in five categories: (1) multiscale feature learning; (2) transformer-based architectures; (3) context-aware methods; (4) data augmentation enhancements; and (5) advancements to mainstream detectors (e.g., YOLO). Third, we describe and analyze the evolving SOD-centered datasets and benchmarks and establish the importance of evaluating models fairly. Fourth, we contribute a comparative assessment of state-of-the-art models, evaluating not only accuracy (e.g., the average precision for small objects (AP_S)) but also important efficiency (FPS, latency, parameters, GFLOPS) metrics across standardized hardware platforms, including edge devices. We further use data-driven case studies in the remote sensing, manufacturing, and healthcare domains to create a bridge between academic benchmarks and real-world performance. Finally, we summarize practical guidance for practitioners, the model selection decision matrix, scenario-based playbooks, and the deployment checklist. The goal of this work is to help synthesize the recent progress, identify the primary limitations in SOD, and open research directions, including the potential future role of generative AI and foundational models, to address the long-standing data and feature representation challenges that have limited SOD.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/app152211882

Cites

69 of 69 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 22

  1. Wang, 2025, A review of object detection techniques in IoT-based intelligent transportation systems, Comput. Mater. Contin., 84, 125
  2. Nikouei, 2025, Small object detection: A comprehensive survey on challenges, techniques and real-world applications, Intell. Syst. Appl., 27, 200561
  3. Zhao, 2024, Dense tiny object detection: A scene context guided approach and a unified benchmark, IEEE Trans. Geosci. Remote Sens., 62, 5606913
  4. Zhu, H., Xu, C., Yang, W., Zhang, R., Zhang, Y., and Xia, G.S. (2024). Robust tiny object detection in aerial images amidst label noise. arXiv.
  5. Rao, 2025, Exploring the advancements and challenges of object detection in video surveillance through deep learning: A systematic literature review and outlook, J. Theor. Appl. Inf. Technol., 103, 6
  6. Dalal, 2025, A systematic review of deep learning-based object detection in agriculture: Methods, challenges, and future directions, Comput. Mater. Contin., 84, 57
  7. Gonsalves, 2025, A systematic review of pedestrian detection techniques using deep learning, Intell. Comput. Commun. Tech., 1, 448
  8. Sundaralingam, H. (2025). Advancing Object Detection Models: An Investigation Focused on Small Object Detection in Complex Scenes. [Ph.D. Thesis, Lakehead University].
  9. Rekavandi, 2025, Transformers in small object detection: A benchmark and survey of state-of-the-art, ACM Comput. Surv., 58, 64
  10. Ferreira, A.D.S., Ramos, A.P.M., Junior, J.M., and Gonçalves, W.N. (2025). Data augmentation and resolution enhancement using GANs and diffusion models for tree segmentation. arXiv.
  11. Zhu, M., Zhong, H., Zhao, C., Du, Z., Huang, Z., Liu, M., Chen, H., Zou, C., Chen, J., and Yang, M. (2025). Active-O3: Empowering multimodal large language models with active perception via GRPO. arXiv.
  12. Liu, 2025, Exploring lightweight structures for tiny object detection in remote sensing images, IEEE Trans. Geosci. Remote Sens., 63, 5623215
  13. Liu, Z., Jiang, H., Zhong, T., Wu, Z., Ma, C., Li, Y., Yu, X., Zhang, Y., Pan, Y., and Shu, P. (2023). Holistic evaluation of GPT-4V for biomedical imaging. arXiv.
  14. Bong, H.M., de Azambuja, R., and Beltrame, G. (2024). BlabberSeg: Real-time embedded open-vocabulary aerial segmentation. arXiv.
  15. Ayoub, K. (2025). Dissertation Submitted to the Department of Computer Science in Partial Fulfillment of the Requirements for Engineer’s Degree in Computer Science Specialty. [Engineer’s Thesis, Higher School of Computer Science].
  16. Raza, S.M., Abidi, S.M.H., Masuduzzaman, M., and Shin, S.Y. (2025). Survey on the application with lightweight deep learning models for edge devices. TechRxiv, preprint.
  17. Leonardis, 2025, SAMFusion: Sensor-adaptive multimodal fusion for 3D object detection in adverse weather, Computer Vision—ECCV 2024, Proceedings of the 18th European Conference, Milan, Italy, 29 September–4 October 2024, Volume 15119, 484
  18. Ghatee, 2023, State-of-the-art analysis of the performance of the sensors utilized in autonomous vehicles in extreme conditions, Artificial Intelligence and Smart Vehicles ICAISV 2023, Volume 1883, 137
  19. Sharma, M. (2024). Multimodal Data Fusion and Model Compression Methods for Computer Vision. [Ph.D. Thesis, Rochester Institute of Technology].
  20. Hamidouche, 2025, Designing object detection models for TinyML: Foundations, comparative analysis, challenges, and emerging solutions, ACM Comput. Surv., 58, 50
  21. Giacalone, E. (2025). AI-Powered Autonomous Industrial Monitoring: Integrating Robotics, Computer Vision, and Generative AI. [Ph.D. Thesis, Politecnico di Torino]. Available online: https://webthesis.biblio.polito.it/35371/.
  22. Sapkota, R., Roumeliotis, K.I., Cheppally, R.H., Flores Calero, M., and Karkee, M. (2025). A review of 3D object detection with vision–language models. arXiv.

Metadata

Authors
Aldubaikhi, A., & Patel, S.
Venue
Applied Sciences
Publisher
MDPI AG
Published
2025-11-07
Volume
15
Issue
22
Pages
11882
ISSN
2076-3417
Cited by
59
References
69
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.