To address the problems of difficult novel-category detection and unstable pseudo-label filtering quality in open-set object detection in remote sensing images, an open-set object detection method for remote sensing images is investigated. A teacher-student detection framework combining Expert Aux (EA) and Class-Adaptive Pseudo-Label Selection (CALS) is proposed. The method uses a visual-semantic teacher network to generate candidate pseudo-labels for novel categories. EA enhances the object-discriminative capability of region features and improves the detectability of novel-category objects. Meanwhile, CALS dynamically determines filtering thresholds according to the confidence distributions of different novel categories, thereby improving pseudo-label quality and training stability. Experiments are conducted on two open-set remote sensing object detection benchmarks, VisDroneZSD and DIOR. The results show that the proposed method achieves 43.38% mAP, 51.84% novel-category mAP, and 45.95% HM on VisDroneZSD, and achieves 63.69%, 47.22%, and 55.67% on DIOR, respectively. Compared with the base model, the full model improves novel-category mAP by 10.87 percentage points and HM by 5.03 percentage points. Ablation experiments and mechanism analysis show that EA improves the detectability of novel-category objects, while CALS improves the quality of novel-category pseudo-labels, demonstrating the effectiveness of the proposed method for open-set object detection in remote sensing images.
[1] ZHANG X, ZHANG T, WANG G, et al. Remote sensing object detection meets deep learning: A metareview of challenges and advances[J]. IEEE Geoscience and Remote Sensing Magazine, 2023, 11(4): 8-44.
[2] 范天麒, 邹征夏, 史振威. 基于强化学习数据合成的典型遥感目标检测[J]. 航空学报, 2025, 46(23): 150-168.
[3] LI K, WAN G, CHENG G, et al. Object detection in optical remote sensing images: A survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296-307.
[4] GUI S, SONG S, QIN R, et al. Remote sensing object detection in the deep learning era—A review[J]. Remote Sensing, 2024, 16(2): 327.
[5] ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(11): 7380-7399.
[6] 支元杰, 葛欣, 张帆, 等. 一种基于混合专家组的多模态航天遥感图像统一检测模型[J/OL]. 航空学报, 2025: 1-17.
[7] WU J, LI X, XU S, et al. Towards open vocabulary learning: A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(7): 5092-5113.
[8] RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[C]//International Conference on Machine Learning. 2021: 8748-8763.
[9] GU X, LIN T Y, KUO W, et al. Open-vocabulary object detection via vision and language knowledge distillation[C]//International Conference on Learning Representations. 2022.
[10] LI L H, ZHANG P, ZHANG H, et al. Grounded language-image pre-training[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 10965-10975.
[11] ZANG Y, LI W, ZHOU K, et al. Open-vocabulary DETR with conditional matching[C]//European Conference on Computer Vision. 2022: 106-122.
[12] ZHOU X, GIRDHAR R, JOULIN A, et al. Detecting twenty-thousand classes using image-level supervision[C]//European Conference on Computer Vision. 2022: 350-368.
[13] LIU S, ZENG Z, REN T, et al. Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection[C]//European Conference on Computer Vision. 2024: 38-55.
[14] CHENG T, SONG L, GE Y, et al. YOLO-World: Real-time open-vocabulary object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024: 16901-16911.
[15] LIU F, CHEN D, GUAN Z, et al. RemoteCLIP: A vision language foundation model for remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5622216.
[16] ZHANG Z, ZHAO T, GUO Y, et al. RS5M and GeoRSCLIP: A large-scale vision-language dataset and a large vision-language model for remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5642123.
[17] LI Y, GUO W, YANG X, et al. Toward open vocabulary aerial object detection with CLIP-activated student-teacher learning[C]//European Conference on Computer Vision. 2024: 431-448.
[18] PAN J, LIU Y, FU Y, et al. Locate anything on earth: Advancing open-vocabulary object detection for remote sensing community[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2025, 39(6): 6281-6289.
[19] HUANG Z, FENG Y, YANG S, et al. OpenRSD: Towards open-prompts for object detection in remote sensing images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2025.
[20] WEI G, YUAN X, LIU Y, et al. OVA-DETR: Open vocabulary aerial object detection using image-text alignment and fusion[DB/OL]. arXiv:2408.12246, 2024.
[21] XIA G S, BAI X, DING J, et al. DOTA: A large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018: 3974-3983.
[22] AISKYEYE TEAM. Zero-shot object detection challenge[EB/OL]. 2023[2023-11-09]. http://aiskyeye.com/challenge-2023/zero-shot-object-detection/.
[23] YANG X, YANG J, YAN J, et al. SCRDet: Towards more robust detection for small, cluttered and rotated objects[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 8232-8241.
[24] XU C, WANG J, YANG W, et al. RFLA: Gaussian receptive field based label assignment for tiny object detection[C]//European Conference on Computer Vision. 2022: 526-543.
[25] 杨永刚, 姜文韬, 高志云. 低空无人机实时目标检测算法[J]. 航空学报, 2025, 46(16): 215-228.
[26] MIN L, FAN Z, LV Q, et al. YOLO-DCTI: Small object detection in remote sensing based on contextual transformer enhancement[J]. Remote Sensing, 2023, 15(16): 3970.
[27] 卢光宇, 陈博文, 陈科研, 等. 基于混合专家模型的航天遥感图像目标检测[J/OL]. 航空学报, 2025: 1-15.
[28] ZAREIAN A, ROSA K D, HU D H, et al. Open-vocabulary object detection using captions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 14393-14402.
[29] TARVAINEN A, VALPOLA H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results[C]//Advances in Neural Information Processing Systems. 2017.
[30] SOHN K, ZHANG Z, LI C L, et al. A simple semi-supervised learning framework for object detection[DB/OL]. arXiv:2005.04757, 2020.
[31] LIU Y C, MA C Y, HE Z, et al. Unbiased teacher for semi-supervised object detection[C]//International Conference on Learning Representations. 2021.
[32] XU M, ZHANG Z, HU H, et al. End-to-end semi-supervised object detection with soft teacher[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 3060-3069.
[33] ZHOU Q, YU C, WANG Z, et al. Instant-Teaching: An end-to-end semi-supervised object detection framework[C]//Proceedings of the IEEE/CVF Conference on Computer Vision. 2021: 4081-4090.
[34] 成桢灏, 杨小冈, 卢瑞涛, 等. 基于多阶段蒸馏的无人机图像时敏目标增量检测算法[J]. 航空学报, 2025, 46(24): 187-203.
[35] WANG S, SONG Y, XIANG J, et al. Mask-guided teacher-student learning for open-vocabulary object detection in remote sensing images[J]. Remote Sensing, 2025, 17(19): 3385.
CJA