{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:01:24Z","timestamp":1790834484440,"version":"4.1.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Autonomous unmanned aerial vehicles (UAVs) depend on onboard perception as the front end of their sensing-decision-control loop, where each detection feeds directly into the navigation, avoidance, and tracking decisions made in flight. Yet detectors trained at one altitude routinely degrade when the platform is redeployed at another, because the underlying distribution shift couples scale, viewpoint, and target density. This study addresses the cross-altitude transfer gap by proposing CADA-Net, an altitude-conditioned detector for onboard UAV perception that treats altitude as an exploitable domain variable rather than a nuisance to be removed. The framework injects a categorical altitude prior into multi-scale features through feature-wise linear modulation, aligns cross-altitude representations via a gradient-reversal adversarial discriminator attached to each pyramid level, and generates target-domain pseudo-supervision through a weak-to-strong teacher-student self-training stream, all sharing a single conditioned encoder. Together these components target not raw recognition accuracy alone but perception that remains stable as the platform\u2019s viewing geometry and object density change through flight. Evaluated on the UAVDT benchmark under a low\u202f\u2192\u202fhigh adaptation protocol, CADA-Net reaches 46.3 mAP@0.5 on the high-altitude band, surpassing the source-only baseline by 17.9 points and the strongest domain-adaptive competitor by 7.2 points, while leaving only a 6.3-point gap to a fully-supervised upper bound; with 5% of target labels, accuracy rises to 48.1 mAP@0.5. Onboard profiling on a Jetson AGX Orin sustains 42 FPS at INT8 precision within a 27.4\u202fW envelope, indicating that the accuracy gain survives the throughput and power limits of embedded inference, which is a precondition for onboard use rather than evidence of closed-loop flight. These findings indicate that rendering a geometric prior explicit can support label-efficient perception at embedded inference rates for UAV platforms operating across altitude transitions.<\/jats:p>","DOI":"10.3389\/fnbot.2026.1926034","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:40:57Z","timestamp":1790833257000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CADA-Net: cross-altitude domain-adaptive perception for label-efficient onboard sensing in autonomous UAVs"],"prefix":"10.3389","volume":"20","author":[{"given":"Liya","family":"Cai","sequence":"first","affiliation":[{"name":"School of Intelligent Management, Suzhou Industrial Park Institute of Services Outsourcing","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"ref1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cao","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"101626","DOI":"10.1016\/j.swevo.2024.101626","article-title":"From PID to swarms: a decade of advancements in drone control and path planning\u2014a systematic review (2013\u20132023)","volume":"89","author":"Cetinsaya","year":"2024","journal-title":"Swarm Evol. Comput."},{"key":"ref3","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2018"},{"key":"ref4","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2021"},{"key":"ref5","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Du","year":"2018"},{"key":"ref6","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"686","DOI":"10.3390\/drones8110686","article-title":"Drones in precision agriculture: a comprehensive review of applications, technologies, and challenges","volume":"8","author":"Guebsi","year":"2024","journal-title":"Drones"},{"key":"ref8","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"13985","DOI":"10.1109\/tvt.2023.3285595","article-title":"Asynchronous curriculum experience replay: a deep reinforcement learning approach for UAV autonomous motion control in unknown dynamic environments","volume":"72","author":"Hu","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.02988","article-title":"Yolov5, Yolov8 and Yolov10: the go-to detectors for real-time vision","author":"Hussain","year":"2024","journal-title":"arXiv Preprint arXiv:2407.02988"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2024.3381272","article-title":"MFFSODNet: multiscale feature fusion small object detection network for UAV aerial images","volume":"73","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref12","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Kennerley","year":"2024"},{"key":"ref13","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1513354","DOI":"10.3389\/fnbot.2024.1513354","article-title":"Navblip: a visual-language model for enhancing unmanned aerial vehicles navigation and object detection","volume":"18","author":"Li","year":"2025","journal-title":"Front. Neurorobot."},{"key":"ref15","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Lin","year":"2017"},{"key":"ref16","article-title":"Unbiased teacher for semi-supervised object detection","author":"Liu","year":"2021","journal-title":"arXiv Preprint arXiv:2102.09480"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2024.3385318","article-title":"A lightweight CNN-transformer network with Laplacian loss for low-altitude UAV imagery semantic segmentation","volume":"62","author":"Lu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"3266","DOI":"10.3390\/rs15133266","article-title":"Unmanned aerial vehicles for search and rescue: a survey","volume":"15","author":"Lyu","year":"2023","journal-title":"Remote Sens."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"40532","DOI":"10.1109\/jiot.2024.3451248","article-title":"Mission planning of UAVs and CAVs based on graph neural network transformer model","volume":"11","author":"Ma","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"14353","DOI":"10.1109\/TPAMI.2023.3290135","article-title":"Domain adaptive object detection via balancing between self-training and adversarial learning","volume":"45","author":"Munir","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"4018","DOI":"10.1109\/tpami.2022.3217046","article-title":"Unsupervised domain adaptation of object detectors: a survey","volume":"46","author":"Oza","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref22","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Perez","year":"2018"},{"key":"ref23","volume-title":"Advances in Neural Information Processing Systems","author":"Ren","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"10990","DOI":"10.1038\/s41598-025-96024-4","article-title":"Monocular depth estimation via a detail semantic collaborative network for indoor scenes","volume":"15","author":"Song","year":"2025","journal-title":"Sci. Rep."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"114439","DOI":"10.1016\/j.engappai.2026.114439","article-title":"A visual attention-guided approach for concrete crack detection in complex environments","volume":"173","author":"Song","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref26","volume-title":"Advances in Neural Information Processing Systems","author":"Tarvainen","year":"2017"},{"key":"ref27","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2024"},{"key":"ref28","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wu","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2024.3506630","article-title":"Localization, balance, and affinity: a stronger multifaceted collaborative salient object detector in remote sensing images","volume":"63","author":"Xie","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"103950","DOI":"10.1016\/j.jag.2024.103950","article-title":"Landslide extraction from aerial imagery considering context association characteristics","volume":"131","author":"Xie","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"8982","DOI":"10.1109\/jstars.2023.3317500","article-title":"A survey on UAV applications in smart city management: challenges, advances, and opportunities","volume":"16","author":"Xu","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s11263-019-01266-1","article-title":"The unmanned aerial vehicle benchmark: object detection, tracking and baseline","volume":"128","author":"Yu","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/lgrs.2023.3265995","article-title":"Self-attention guidance and multiscale feature fusion-based Uav image object detection","volume":"20","author":"Zhang","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"9161","DOI":"10.1109\/TPAMI.2024.3416098","article-title":"Robust domain adaptive object detection with unified multi-granularity alignment","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref35","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/tpami.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1926034\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:41:03Z","timestamp":1790833263000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1926034\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":36,"alternative-id":["10.3389\/fnbot.2026.1926034"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2026.1926034","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"article-number":"1926034"}}