The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
DUST-YOLO: A Deployable UAV Swin Transformer YOLO with Multi-Dimensional Pruning and Mixed-Precision Quantization for End-to-End Video Object Detection
Abstract
Real-time video object detection on unmanned aerial vehicles (UAVs) is essential for urban inspection and autonomous perception, yet its deployment on edge devices is severely constrained by the high computational cost of accurate detectors, the quantization sensitivity of hybrid convolution-attention networks, and the system-level latency of full video processing pipelines. To address these challenges, we present DUST-YOLO, a deployment-oriented algorithm-hardware co-design framework, where structured pruning and mixed-precision quantization-aware training (QAT) are jointly optimized with TensorRT–DeepStream for efficient UAV small-object detection on edge platforms. First, we introduce a multi-dimensional structured pruning strategy that applies asymmetric channel pruning to convolutional and feature-fusion modules while compressing the Swin Transformer prediction heads and bottleneck stacks, thereby reducing parameters and computation with limited impact on multi-scale representation capability. Second, we develop a hardware-aware mixed-precision QAT scheme that maps computation-intensive backbone layers to INT8 while preserving the Transformer-related modules in FP16, improving inference efficiency while mitigating the accuracy loss caused by uniform low-bit quantization. Third, we compile the optimized network with TensorRT and integrate the resulting inference engine into a DeepStream-based asynchronous video pipeline on the edge platform, enabling end-to-end acceleration by reducing decoding, preprocessing, and memory-transfer overheads. Experimental results on the VisDrone2019-DET dataset and the NVIDIA Jetson Orin NX demonstrate that DUST-YOLO achieves 43.7% mAP@0.5 accuracy with an end-to-end latency of 36.3 ms and a throughput of 27.5 FPS. Compared with the state of the art, DUST-YOLO reduces end-to-end latency by 56.9% and improves end-to-end video throughput by 2.31×.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Li, Z., Xiao, J., Yang, L., & Gu, Q. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01580 · Cited by 127
EL-YOLO: An efficient and lightweight low-altitude aerial objects detector for onboard applications
Xue, C., Xia, Y., Wu, M., Chen, Z., Cheng, F., & Yun, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124848 · Cited by 82
Aljami, H. M., Alrowais, N. A., AlAwajy, A. M., Alhrgan, S. O., Aldwaani, R. A., Alsawadi, M. S., Saqib, N. U., Alam, S. S., & Alsubaie, R. (2026) · Computers · doi:10.3390/computers15020074 · Cited by 24
Research works printed but not linked: 34
- Echchidmi, M., and Bouayad, A. (2026). TinyML for sustainable edge intelligence: Practical optimization under extreme resource constraints. Technologies, 14. · DOI
- Shih, W.-C., Wang, Z.-Y., Kristiani, E., Hsieh, Y.-J., Sung, Y.-H., Li, C.-H., and Yang, C.-T. (2025). The construction of a stream service application with DeepStream and simple realtime server using containerization for edge computing. Sensors, 25. · DOI
- Gong, J., Yuan, Z., Li, W., Li, W., Guo, Y., and Guo, B. (2026). A Lightweight Upsampling and Cross-Modal Feature Fusion-Based Algorithm for Small-Object Detection in UAV Imagery. Electronics, 15. · DOI
- Jiang, Z., Li, C., Qu, T., He, C., and Wang, D. (2025). MSQuant: Efficient post-training quantization for object detection via migration scale search. Electronics, 14. · DOI · Paper page
- Tian, L., and Wang, P. (2025). An effective mixed-precision quantization method for joint image deblurring and edge detection. Electronics, 14. · DOI
- Sun, J., Gao, H., Yan, Z., Qi, X., Yu, J., and Ju, Z. (2024). Lightweight UAV Object-Detection Method Based on Efficient Multidimensional Global Feature Adaptive Fusion and Knowledge Distillation. Electronics, 13. · DOI
- Yang, R., Li, W., Shang, X., Zhu, D., and Man, X. (2023). KPE-YOLOv5: An improved small target detection algorithm based on YOLOv5. Electronics, 12. · DOI
- Wang, K., Zhou, H., Wu, H., and Yuan, G. (2024). RN-YOLO: A Small Target Detection Model for Aerial Remote-Sensing Images. Electronics, 13. · DOI
- Zhu, 2026, Real-time object detection for unmanned aerial vehicles based on vision transformer and edge computing, Sci. Rep., 16, 6814, 10.1038/s41598-026-37938-5 · DOI
- Zhu, X., Lyu, S., Wang, X., and Zhao, Q. (2021, January 11–17). TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, QC, Canada. · DOI
- Zhao, Q., Liu, B., Lyu, S., Wang, C., and Zhang, H. (2023). TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer. Remote Sens., 15. · DOI
- Shi, 2024, P2-ViT: Power-of-two post-training quantization and acceleration for fully quantized vision transformer, IEEE Trans. Very Large Scale Integr. (VLSI) Syst., 32, 1704, 10.1109/TVLSI.2024.3422684 · DOI
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 4). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria. Available online: https://openreview.net/forum?id=YicbFdNTTy.
- Hakani, R., and Rawat, A. (2024). Edge computing-driven real-time drone detection using YOLOv9 and NVIDIA Jetson Nano. Drones, 8. · DOI
- Wu, 2025, Enhanced feature representation for real time UAV image object detection using contextual information and adaptive fusion, Sci. Rep., 15, 33711, 10.1038/s41598-025-19145-w · DOI
- Zhao, 2025, PSO-YOLO: A contextual feature enhancement method for small object detection in UAV aerial images, Earth Sci. Inform., 18, 258, 10.1007/s12145-025-01780-6 · DOI
- Cai, S., Wu, Z., Liu, K., Zhang, T., Weng, W., and Zheng, X. (2026). LSOD-YOLO: A visual object detection method for AGV perception systems based on a lightweight backbone and detection head. Technologies, 14. · DOI
- Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–22). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA. · DOI · Paper page
- Mi, Q., Chao, J., Chen, A., Zhang, K., and Lai, J. (2026). YOLO11s-UAV: An Advanced Algorithm for Small Object Detection in UAV Aerial Imagery. J. Imaging, 12. · DOI
- Fan, 2025, LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle, Inf. Sci., 686, 121366, 10.1016/j.ins.2024.121366 · DOI
- Huang, M., Mi, W., and Wang, Y. (2024). EDGS-YOLOv8: An improved YOLOv8 lightweight UAV detection model. Drones, 8. · DOI
- Xie, S., Deng, G., Lin, B., Jing, W., Li, Y., and Zhao, X. (2024). Real-time object detection from UAV inspection videos by combining YOLOv5s and DeepStream. Sensors, 24. · DOI
- Barthelemy, J., Iqbal, U., Qian, Y., Amirghasemi, M., and Perez, P. (2024). Safety after dark: A privacy compliant and real-time edge computing intelligent video analytics for safer public transportation. Sensors, 24. · DOI
- Yue, M., Zhang, L., Huang, J., and Zhang, H. (2024). Lightweight and efficient tiny-object detection based on improved YOLOv8n for UAV aerial images. Drones, 8. · DOI
- Liu, 2024, YOLC: You only look clusters for tiny object detection in aerial images, IEEE Trans. Intell. Transp. Syst., 25, 13863, 10.1109/TITS.2024.3386928 · DOI
- Ma, 2023, YOLO-UAV: Object detection method of unmanned aerial vehicle imagery based on efficient multi-scale feature fusion, IEEE Access, 11, 126857, 10.1109/ACCESS.2023.3329713 · DOI
- Cao, Y., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Van Gool, L., and Han, J. (2021, January 11–17). VisDrone-DET2021: The vision meets drone object detection challenge results. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, QC, Canada. · DOI
- Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., and Tian, Q. (2018, January 8–14). The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. · DOI · Paper page
- Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (October, January 29). YOLOv9: Learning what you want to learn using programmable gradient information. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy.
- Wang, 2024, YOLOv10: Real-Time End-to-End Object Detection, Adv. Neural Inf. Process. Syst., 37, 107984
- Tian, 2026, YOLOv12: Attention-Centric Real-Time Object Detectors, Adv. Neural Inf. Process. Syst., 38, 78433
- Gao, F., An, J., Zhang, M., Chen, X., and Zhao, Q. (2025, January 28–30). FE-YOLO: A Traffic Target Detection Network Based on YOLOv11n. Proceedings of the 2025 44th Chinese Control Conference (CCC), Chongqing, China. · DOI
- Jiang, 2022, A review of YOLO algorithm developments, Procedia Comput. Sci., 199, 1066, 10.1016/j.procs.2022.01.135 · DOI · Paper page
- Terven, 2023, A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS, Mach. Learn. Knowl. Extr., 5, 1680, 10.3390/make5040083 · DOI
Metadata
- Authors
- Lin, G., Jiang, J., Cai, J., Luo, X., Wang, Z., Sun, H., & Pu, Z.
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2026-06-11
- Volume
- 15
- Issue
- 12
- Pages
- 2579
- ISSN
- 2079-9292
- Cited by
- 1
- References
- 5
- Language
- en
- Funders
- Southeast University Interdisciplinary Research Program for Young Scholars (2024FGC1006)
- National Natural Science Foundation of China (52525204, 52572354)
- Jiangsu International Collaborative Research Project (BZ2024055)
- National Undergraduate Training Programs for Innovation (202510286051)
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: DUST-YOLO: A Deployable UAV Swin Transformer YOLO with Multi-Dimensional Pruning and Mixed-Precision Quantization for End-to-End Video Object Detection. https://app.cochat.ai/papers/10.3390/electronics15122579
- The paper
- Lin, G., Jiang, J., Cai, J., Luo, X., Wang, Z., Sun, H., & Pu, Z. (2026). DUST-YOLO: A Deployable UAV Swin Transformer YOLO with Multi-Dimensional Pruning and Mixed-Precision Quantization for End-to-End Video Object Detection. Electronics. https://doi.org/10.3390/electronics15122579
