基于步进式自适应特征融合模块的小目标检测网络

doi:10.3778/j.issn.1002-8331.2409-0081

摘要/Abstract

摘要： 小目标检测在驾驶辅助、智慧医疗、无人机巡检等任务中具有重要的理论和实践意义。多尺度特征学习是设计小目标检测网络经常采用的策略之一。其中，经典的特征金字塔结构通过融合不同层级的特征图，实现多尺度信息的传递，从而在不同分辨率的特征图上都能捕捉到小目标的关键信息。然而，在进行不同尺度特征图融合时，语义信息冲突往往不可避免，进而造成梯度计算不一致，导致小目标信息被淹没。为此，提出了一种步进式自适应特征融合网络模块（step-by-step adaptively feature fusion module，SAFF），将特征融合过程划分为三个阶段依次进行，通过步进式地融合相邻尺度特征图，解决特征图融合过程中的语义信息冲突问题。同时，在每个阶段中，通过自适应计算融合权重，缓解梯度计算不一致问题。在此基础上，将SAFF模块与通用目标检测网络结合，形成用于小目标检测的SAFF-RCNN和Cascade-SAFF-RCNN网络。实验结果表明，所提出的网络模型的小目标检测性能均有显著提升，达到或超越了其他主流的小目标检测模型，证明了SAFF模块用于小目标检测时的有效性。

关键词: 小目标检测, 多尺度特征融合, 自适应融合

Abstract: Small object detection plays a role in tasks such as driving assistance, smart healthcare, and drone inspections. Multi-scale feature learning is a commonly adopted strategy in designing small object detection networks. The classic feature pyramid structure achieves multiscale information transmission by integrating feature maps from different levels, thereby capturing key information about small objects across feature maps of varying resolutions. However, when fusing feature maps at different scales, semantic information conflicts often arise, leading to inconsistent gradient computations and causing the information of small objects to be overwhelmed. Therefore, a step-by-step adaptive feature fusion module (SAFF) is proposed, which divides the feature fusion process into three sequential stages. By progressively fusing adjacent scale feature maps, it resolves the issue of semantic conflict during the fusion process. Additionally, within each stage, adaptive feature fusion can alleviate the problem of inconsistent gradient calculations. The SAFF module is applied to general object detection networks to form the SAFF-RCNN and Cascade-SAFF-RCNN networks dedicated to small object detection. Experimental results show that the proposed networks achieve significant improvements in small object detection performance, reaching or surpassing other mainstream small object detection models, thus demonstrating the effectiveness of the proposed SAFF module in small object detection.

Key words: small object detection, multi-scale feature fusion, adaptive fusion

陈鹏, 林斌, 白勇, 黄伟伦. 基于步进式自适应特征融合模块的小目标检测网络[J]. 计算机工程与应用, 2025, 61(23): 224-232.

CHEN Peng, LIN Bin, BAI Yong, HUANG Weilun. Small Object Detection Network Based on Step-by-Step Adaptively Feature Fusion Module[J]. Computer Engineering and Applications, 2025, 61(23): 224-232.

参考文献

[1] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2014: 740-755.
[2] CHENG G, YUAN X, YAO X W, et al. Towards large-scale small object detection: survey and benchmarks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023: 1-20.
[3] WANG J W, YANG W, GUO H W, et al. Tiny object detection in aerial images[C]//Proceedings of the 25th International Conference on Pattern Recognition. Piscataway: IEEE, 2021: 3791-3798.
[4] YU X H, GONG Y Q, JIANG N, et al. Scale match for tiny person detection[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2020: 1246-1254.
[5] XU C, WANG J W, YANG W, et al. Dot distance for tiny object detection in aerial images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2021: 1192-1201.
[6] YANG C, HUANG Z H, WANG N Y. QueryDet: cascaded sparse query for accelerating high-resolution small object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 13658-13667.
[7] YUAN X, CHENG G, YAN K B, et al. Small object detection via coarse-to-fine proposal generation and imitation learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 6294-6304.
[8] FU R H, CHEN C C, YAN S, et al. Gaussian similarity-based adaptive dynamic label assignment for tiny object detection[J]. Neurocomputing, 2023, 543: 126285.
[9] HOU H Y, SHEN M Y, HSU C C, et al. Ensemble fusion for small object detection[C]//Proceedings of the 18th International Conference on Machine Vision and Applications. Piscataway: IEEE, 2023: 1-6.
[10] 彭晏飞, 赵涛, 陈炎康, 等. 基于上下文信息与特征细化的无人机小目标检测算法[J]. 计算机工程与应用, 2024, 60(5):183-190.
PENG Y F, ZHAO T, CHEN Y K, et al. UAV small object detection algorithm based on context information and feature refinement[J]. Computer Engineering and Applications, 2024, 60(5): 183-190.
[11] ZHAO Z C, DU J X, LI C L, et al. Dense tiny object detection: a scene context guided approach and a unified benchmark[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-13.
[12] 陈商盈, 倪受东, 童林. 改进YOLOX的自动驾驶场景目标检测算法[J]. 计算机工程与应用, 2024, 60(12): 225-233.
CHEN S Y, NI S D, TONG L. Improved YOLOX algorithm for object detection in autonomous driving scenarios[J]. Computer Engineering and Applications, 2024, 60(12): 225-233.
[13] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944.
[14] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768.
[15] LIU S, HUANG D, WANG Y. Learning spatial fusion for single-shot object detection[J]. arXiv:1911.09516, 2019.
[16] GONG Y Q, YU X H, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 1159-1167.
[17] HONG M B, LI S W, YANG Y C, et al. SSPNet: scale selection pyramid network for tiny person detection from UAV images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.
[18] DENG C F, WANG M M, LIU L, et al. Extended feature pyramid network for small object detection[J]. IEEE Transactions on Multimedia, 2022, 24: 1968-1979.
[19] XIAO J S, GUO H W, ZHOU J, et al. Tiny object detection with context enhancement and feature purification[J]. Expert Systems with Applications, 2023, 211: 118665.
[20] ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7380-7399.
[21] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[22] CAI Z, VASCONCELOS N. Cascade R-CNN: high quality object detection and instance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(5): 1483-1498.
[23] TIAN Z, SHEN C, CHEN H, et al. FCOS: a simple and strong anchor-free object detector[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(4): 1922-1933.
[24] ZHANG S F, CHI C, YAO Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9756-9765.
[25] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
[26] GE Z, LIU S, WANG F, et al. YOLOx: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[27] ZHU X, SU W, LU L, et al. Deformable DETR: deformable Transformers for end-to-end object detection[C]//Proceedings of the International Conference on Learning Representations, 2020: 1-16.
[28] SUN P Z, ZHANG R F, JIANG Y, et al. Sparse R-CNN: end-to-end object detection with learnable proposals[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 14449-14458.
[29] XU C, WANG J W, YANG W, et al. RFLA: Gaussian receptive field based label assignment for tiny object detection[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 526-543.
[30] GLENN J. YOLOv8: state-of-the-art object detection and segmentation models[EB/OL]. (2023-01-10)[2024-12-11]. https://github.com/ultralytics/ultralytics/releases/tag/v8.1.0.
[31] CHEN P L, WANG J T, ZHANG Z W, et al. DILA: dynamic gaussian distribution fitting and imitation learning-based label assignment for tiny object detection[J]. Applied Soft Computing, 2024, 164: 111980.
[32] DU B W, HUANG Y C, CHEN J X, et al. Adaptive sparse convolutional networks with global context enhancement for faster object detection on drone images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 13435-13444.