{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:55:46Z","timestamp":1790769346969,"version":"4.1.0"},"reference-count":36,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Aerial scenes exhibit a mismatch between where computation is spent and where information resides: targets occupy a small, unevenly distributed fraction of the frame, yet detectors process every region at identical resolution. Tiling and clustering pipelines exploit this sparsity, but the rule deciding which regions deserve magnification is hand-designed and never observes the detection loss. AFWD-Net removes that separation. A coarse density estimator, run on a heavily downsampled copy of the frame at negligible cost, produces a spatial prior over likely target locations; Gumbel top-K relaxation and a spatial-transformer sampler convert this prior into a small set of high-resolution crops whose centers and scales are differentiable, so the gradient that measures detection quality also determines where resolution is allocated. Within each crop, a learnable wavelet decomposition separates approximation from directional detail sub-bands and enhances the latter under edge supervision confined to annotated regions, restoring the high-frequency structure that stride downsampling erases, precisely the cue separating a genuine sub-32-pixel target from background clutter. Detection queries are seeded from the same density field rather than a fixed lattice, and crop-level predictions are merged by density-calibrated soft suppression. On VisDrone2019-DET the model attains 49.3% mAP@0.5, 30.4% mAP@[0.5:0.95] and 22.8% APS at 15.7 M parameters; a distilled 7.2 M student remains competitive with all compared methods. Experiments on UAVDT, AI-TOD-v2 and SODA-A assess cross-dataset generalization.<\/jats:p>","DOI":"10.3390\/s26196157","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:57:57Z","timestamp":1790611077000},"page":"6157","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Differentiable Resolution Allocation for Tiny Object Detection in UAV Imagery"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5206-635X","authenticated-orcid":false,"given":"Ergashevich Halimjon","family":"Khujamatov","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Gyeonggi-go, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5285-3775","authenticated-orcid":false,"given":"Khasanov","family":"Doston","sequence":"additional","affiliation":[{"name":"Department of Data Communication Networks and Systems,\r\nTashkent University of Information Technologies, Tashkent 100084, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"}]},{"given":"Yusupov Sarvarbek","family":"Sodikovich","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering Kimyo International University in Tashkent, Tashkent 100121, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"project-administration","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1918-0641","authenticated-orcid":false,"given":"Oybek Usmankulovich","family":"Mallaev","sequence":"additional","affiliation":[{"name":"Department of Digital Technologies, Alfraganus University, Yukori Karakamish Street 2a, Tashkent 100190, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6223-4502","authenticated-orcid":false,"given":"Shakhnoza","family":"Muksimova","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Gyeonggi-go, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"project-administration","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Alisher","family":"Mamatov","sequence":"additional","affiliation":[{"name":"Department of Digital Pedagogy and Media Education Development, Republican Scientific and Methodological Center for the Development of Education of the Republic of Uzbekistan, Tashkent 100011, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Jinsoo","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gachon University, Seongnam-si 13120, Gyeonggi-go, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-3306","authenticated-orcid":false,"given":"Razvan","family":"Craciunescu","sequence":"additional","affiliation":[{"name":"Department of Telecommunications, Faculty of Electronics, Telecommunications and Information Technology, National University of Science and Technology POLITEHNICA Bucharest, 060042 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"ref_1","first-page":"200561","article-title":"Small object detection: A comprehensive survey on challenges, techniques and real-world applications","volume":"27","author":"Nikouei","year":"2025","journal-title":"Intell. Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/s10462-025-11150-9","article-title":"A survey of small object detection based on deep learning in aerial images","volume":"58","author":"Hua","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1145\/3664598","article-title":"Recent advances for aerial object detection: A survey","volume":"56","author":"Leng","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Li, J., Ou, C., Yan, D., Zhang, H., and Xue, X. (2025). Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives. Drones, 9.","DOI":"10.3390\/drones9080557"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, H., Zhang, W., Ma, J., Li, C., Ding, Y., and Zhang, Z. (2025). MSUD-YOLO: A novel multiscale small object detection model for UAV aerial images. Drones, 9.","DOI":"10.3390\/drones9060429"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Akhmedov, F., Khasanov, D., Yusupov, S.S., Mallaev, O.U., Khujamatov, H.E., Khujakulov, T.A., and Cho, Y.I. (2026). AH-YOLOFlow: Vision-Based Pedestrian Flow Analytics for Smart Urban Crosswalk Performance Monitoring. Sustainability, 18.","DOI":"10.3390\/su18179040"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, G., Peng, Y., and Li, J. (2025). YOLO-MARS: An enhanced YOLOV8N for small object detection in UAV aerial imagery. Sensors, 25.","DOI":"10.3390\/s25082534"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, W., Sun, C., He, R., and Zhang, Y. (2024). HSP-YOLOv8: UAV aerial photography small target detection algorithm. Drones, 8.","DOI":"10.3390\/drones8090453"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ciccone, F., and Ceruti, A. (2025). Real-time search and rescue with drones: A deep learning approach for small-object detection based on YOLO. Drones, 9.","DOI":"10.3390\/drones9080514"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Akhmedov, F., Khasanov, D., Yusupov, S.S., Mallaev, O.U., Khujamatov, H.E., Khujakulov, T.A., and Cho, Y.I. (2026). Attention-Enhanced YOLOv11 for Early Detection of Fungal-Induced Forest Tree Decline. Plants, 15.","DOI":"10.3390\/plants15172609"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Di, X., Cui, K., and Wang, R.F. (2025). Toward efficient uav-based small object detection: A lightweight network with enhanced feature fusion. Remote Sens., 17.","DOI":"10.3390\/rs17132235"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xie, H., Wang, M., Cao, R., Wang, J., Jiang, Y., Huang, Q., and Jiang, L. (2025). MTD-YOLO: A Multi-Scale Perception Framework with Task Decoupling and Dynamic Alignment for UAV Small Object Detection. Remote Sens., 17.","DOI":"10.3390\/rs17233823"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wan, Z., Lan, Y., Xu, Z., Shang, K., and Zhang, F. (2025). DAU-YOLO: A lightweight and effective method for small object detection in UAV images. Remote Sens., 17.","DOI":"10.3390\/rs17101768"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.1038\/s41598-025-32074-y","article-title":"Enhanced small object detection in UAV aerial imagery through attention gated backbone and context aware fusion","volume":"16","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s40747-025-02126-x","article-title":"A UAV aerial image small object detection algorithm based on fine-grained feature preservation and multi-scale feature pyramid balancing","volume":"12","author":"Luo","year":"2026","journal-title":"Complex Intell. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1080\/19475683.2026.2617202","article-title":"RE-YOLO: A lightweight small object detection method for UAV remote sensing imagery","volume":"32","author":"Wang","year":"2026","journal-title":"Ann. GIS"},{"key":"ref_17","unstructured":"Bellec, Y.V. (2026). DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hu, Z., Wu, P., Chen, J., Zhu, H., Wang, Y., Peng, Y., Li, H., and Sun, X. (2025, January 27\u201331). Dome-DETR: DETR with density-oriented feature-query manipulation for efficient tiny object detection. Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland.","DOI":"10.1145\/3746027.3754861"},{"key":"ref_19","unstructured":"Wen, Z., Yang, Z., Bao, X., Zhang, L., Xiang, X., Li, W., and Liu, Y. (2026). D3R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liang, B., Wei, H., Liu, Y., Qiu, B., Wang, Y., Sui, X., and Chen, Q. (2025). FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection. arXiv.","DOI":"10.1109\/TGRS.2026.3737768"},{"key":"ref_21","unstructured":"Moretti, F., Jin, Y., and Mario, G. (2026). Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1109\/TIP.2024.3501853","article-title":"ESOD: Efficient small object detection on high-resolution images","volume":"34","author":"Liu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"ref_23","unstructured":"Li, Y., Liu, Q., Jin, Z., Wei, J., Nie, J., and Fu, Y. (2025). MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection. arXiv."},{"key":"ref_24","unstructured":"Wang, S., Chen, Z., Cao, L., and Ji, R. (2025). Purifying, labeling, and utilizing: A high-quality pipeline for small object detection. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Umirzakova, S., Muksimova, S., Shavkatovich Buriboev, A., Primova, H., and Choi, A.J. (2025). A Unified Transformer Model for Simultaneous Cotton Boll Detection, Pest Damage Segmentation, and Phenological Stage Classification from UAV Imagery. Drones, 9.","DOI":"10.3390\/drones9080555"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zheng, W., Xiong, B., Chen, J., Ou, Q., and Yu, L. (2025). A Texture Reconstructive Downsampling for Multi-Scale Object Detection in UAV Remote-Sensing Images. Sensors, 25.","DOI":"10.3390\/s25051569"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jin, B., Yin, F., Cai, W., Li, H., Zhu, H., Huang, W., Wu, Q., Chen, H., and Sun, Z. (2025). HWANet: A Haar Wavelet-based Attention Network for remote sensing object detection. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0330759"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e70419","DOI":"10.1002\/cpe.70419","article-title":"DWT-YOLO: Wavelet-Based Detection to Enhance Sensor Resolution for Small Targets","volume":"37","author":"Wu","year":"2025","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Shi, S., Fang, Q., Xu, X., and Zhao, T. (2024). Similarity distance-based label assignment for tiny object detection. 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE.","DOI":"10.1109\/IROS58592.2024.10801448"},{"key":"ref_30","unstructured":"Shi, Z., Hu, J., Ren, J., Ye, H., Yuan, X., Ouyang, Y., He, J., Ji, B., and Guo, J. (March, January 25). HS-FPN: High frequency and spatial perception FPN for tiny object detection. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_31","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","first-page":"1137","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"eaee8014","DOI":"10.1126\/sciadv.aee8014","article-title":"Optical maneuvering of dandelion-inspired fliers with vortex-enabled stability","volume":"12","author":"Yang","year":"2026","journal-title":"Sci. Adv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yeh, J.F., Lin, K.M., Yuan, L.C., and Hsu, J.M. (2024). Automatic counting and location labeling of rice seedlings from unmanned aerial vehicle images. Electronics, 13.","DOI":"10.3390\/electronics13020273"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"8197","DOI":"10.1109\/TCSVT.2025.3544741","article-title":"Learning discriminative representation for fine-grained object detection in remote sensing images","volume":"35","author":"Xie","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6157\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:03:54Z","timestamp":1790766234000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":36,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196157"],"URL":"https:\/\/doi.org\/10.3390\/s26196157","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}