基于特征融合的多属性小目标检测

doi:10.19678/j.issn.1000-3428.0252596

摘要/Abstract

摘要： 目标检测是计算机视觉中的一项基础任务,旨在实现对图像中目标的定位和类别识别。多属性识别则是输入以目标为中心的图像,输出图像中目标的多个属性的分类结果。当前检测算法对小目标识别存在困难,而属性识别算法无法自行定位目标。为此,提出一种多属性小目标检测框架MA-YOLO,以同时完成小目标检测和多属性识别两个任务。首先,该框架通过属性解耦模块(ADM)进行特征解耦,并添加多个并行的属性分类头;其次,为了实现属性间的特征交互,设计一种简单但有效的属性融合策略,通过桥接特征生成模块(BFGM)生成桥接特征,实现骨干网络提取到的特征和后续解耦出来的所有属性特征的过渡,利用属性融合模块(AFM)得到融合后的各个属性特征。针对小目标检测问题,采用一种卷积和自注意力混合(ACmix)模块,以增强网络的特征提取能力。此外,将边界框建模为二维高斯分布,使用归一化Wasserstein距离(NWD)度量。实验结果表明,在多属性数据集WIDER Attribute的测试集和验证集以及小目标数据集VisDrone2019的验证集上,MA-YOLO的mAP@0.5分别达到84.1%、85.3%和48.2%,大量消融和可视化实验也验证了MA-YOLO的有效性。

关键词: 深度学习, 计算机视觉, 目标检测, 多属性, 小目标

Abstract: Object detection is a fundamental task in computer vision, which aims to locate and classify objects within an image. By contrast, multi-attribute recognition involves inputting an image centered around an object and outputting the classification results of multiple attributes of the object within the image. Current detection algorithms face challenges in recognizing small objects, while attribute recognition algorithms fail to locate objects. To address these issues, this paper proposes a multi-attribute small object detection framework, MA-YOLO, that performs small object detection and multi-attribute recognition simultaneously. First, an Attribute Decoupling Module (ADM) decouples attributes of the object and adds multiple parallel attribute classification heads. Second, a simple yet effective attribute-fusion strategy is used to facilitate feature interactions among the attributes. This strategy generates bridging features through a Bridge Feature Generation Module (BFGM) to bridge the gap between the features extracted by the backbone network and all decoupled attribute features, and it utilizes an Attribute Fusion Module (AFM) to obtain fused attribute features. For small object detection, a convolution and self-attention hybrid module, ACmix, is adopted to enhance the feature extraction capability of the network. Additionally, bounding boxes are modeled as two-dimensional Gaussian distributions and measured using the Normalized Wasserstein Distance (NWD). Experimental results show that MA-YOLO achieves mAP@0.5 values of 84.1% and 85.3% on the test and validation sets of the multi-attribute dataset WIDER Attribute and 48.2% as the validation set of the small object dataset VisDrone2019. Extensive ablation and visualization experiments validate the effectiveness of MA-YOLO.

Key words: deep learning, computer vision, object detection, multi-attribute, small object

中图分类号:

TP391.41

辛振伟, 张粼, 王宝龙, 石少华, 杨一鹏, 程辉, 陈涛. 基于特征融合的多属性小目标检测[J]. 计算机工程, 2026, 52(10): 164-176.

XIN Zhenwei, ZHANG Lin, WANG Baolong, SHI Shaohua, YANG Yipeng, CHENG Hui, CHEN Tao. Multi-Attribute Small Object Detection Based on Feature Fusion[J]. Computer Engineering, 2026, 52(10): 164-176.

https://www.ecice06.com/CN/Y2026/V52/I10/164

参考文献

[1] CHIB P S, SINGH P. Recent advancements in end-to-end autonomous driving using deep learning: a survey[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(1): 103-118.
[2] 朱飞宇, 彭敦陆. YOLO-SP: 面向工业安全的局部多尺度目标检测检测网络[J]. 小型微型计算机系统, 2025, 46(6): 1435-1441. ZHU F Y, PENG D L. YOLO-SP: a local multi-scale object detection detection network for industrial safety[J]. Journal of Chinese Computer Systems, 2025, 46(6): 1435-1441. (in Chinese)
[3] 俞益洲, 石德君, 马杰超, 等. 人工智能在医学影像分析中的应用进展[J]. 中国医学影像技术, 2019, 35(12): 1808-1812. YU Y Z, SHI D J, MA J C, et al. Advances in application of artificial intelligence in medical image analysis[J]. Chinese Journal of Medical Imaging Technology, 2019, 35(12): 1808-1812. (in Chinese)
[4] CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C.,USA:IEEE Press,2018: 6154-6162.
[5] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2016: 779-788.
[6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[EB/OL].[2025-04-05]. https://arxiv.org/abs/1512.02325.
[7] WANG X, ZHENG S F, YANG R, et al. Pedestrian attribute recognition: a survey[J]. Pattern Recognition, 2022, 121: 108220.
[8] YE M, SHEN J B, LIN G J, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6): 2872-2893.
[9] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2025-04-05]. https://arxiv.org/abs/1409.1556.
[10] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2015: 1-9.
[11] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2016: 770-778.
[12] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C.,USA:IEEE Press,2014: 580-587.
[13] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C.,USA:IEEE Press,2016: 1440-1448.
[14] 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.
[15] CHENG X H, JIA M X, WANG Q, et al. A simple visual-textual baseline for pedestrian attribute recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(10): 6994-7004.
[16] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL].[2025-04-05]. https://arxiv.org/abs/1706.03762.
[17] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL].[2025-04-05]. https://arxiv.org/abs/2010.11929.
[18] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL].[2025-04-05]. https://arxiv.org/abs/1810.04805.
[19] 火久元, 苏泓瑞, 武泽宇, 等. 基于改进YOLOv8的道路交通小目标车辆检测算法[J]. 计算机工程, 2025, 51(1): 246-257. HUO J Y, SU H R, WU Z Y, et al. Road traffic small target vehicle detection algorithm based on improved YOLOv8[J]. Computer Engineering, 2025, 51(1): 246-257. (in Chinese)
[20] LIU S, CHEN P F, WO AZĆG NIAK M. Image enhancement-based detection with small infrared targets[J]. Remote Sensing, 2022, 14(13): 3232.
[21] 戚欣, 姜春雷. 人工智能助力智慧城市建设[J]. 智能建筑与智慧城市, 2017(9): 33-37. QI X, JIANG C L. Artificial intelligence boosts smart city construction[J]. Intelligent Building & City Information, 2017(9): 33-37. (in Chinese)
[22] PAN X R, GE C J, LU R, et al. On the integration of self-attention and convolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2022: 805-815.
[23] WANG J W, XU C, YANG W, et al. A normalized Gaussian Wasserstein distance for tiny object detection[EB/OL].[2025-04-05]. https://arxiv.org/abs/2110.13389.
[24] LI Y N, HUANG C, LOY C C, et al. Human attribute recognition by deep hierarchical contexts[EB/OL].[2025-04-05]. https://link.springer.com/content/pdf/10.1007/978-3-319-46466-4_41.pdf.
[25] CAO Y R, HE Z J, WANG L J, et al. VisDrone-DET2021: the vision meets drone object detection challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C.,USA:IEEE Press,2021: 2847-2854.
[26] HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C.,USA:IEEE Press,2017: 2980-2988.
[27] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[EB/OL].[2025-04-05]. https://arxiv.org/abs/2005.12872.
[28] ZHU X Z, SU W J, LU L W, et al. Deformable DETR: deformable transformers for end-to-end object detection[EB/OL].[2025-04-05]. https://arxiv.org/abs/2010.04159.
[29] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C.,USA:IEEE Press,2022: 9992-10002.
[30] ZHAO Y A, LÜ W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2024: 16965-16974.
[31] ZHANG N, PALURI M, RANZATO M, et al. PANDA: pose aligned networks for deep attribute modeling[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C.,USA:IEEE Press,2014: 1637-1644.
[32] 陈鸿昶, 吴彦丞, 李邵梅, 等. 基于行人属性分级识别的行人再识别[J]. 电子与信息学报, 2019, 41(9): 2239-2246. CHEN H C, WU Y C, LI S M, et al. Person re-identification based on attribute hierarchy recognition[J]. Journal of Electronics & Information Technology, 2019, 41(9): 2239-2246. (in Chinese)
[33] ZHAO X, SANG L, DING G, et al. Grouping attribute recognition for pedestrian with joint recurrent learning[EB/OL].[2025-04-05]. https://www.ijcai.org/Proceedings/2018/0441.pdf.
[34] 李娜, 武阳阳, 刘颖, 等. 基于多尺度注意力网络的行人属性识别算法[J]. 激光与光电子学进展, 2021, 58(4): 0410025. LI N, WU Y Y, LIU Y, et al. Pedestrian attribute recognition algorithm based on multi-scale attention network[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410025. (in Chinese)
[35] DONG Q, GONG S G, ZHU X T. Multi-task curriculum transfer deep learning of clothing attributes[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV). Washington D.C.,USA:IEEE Press,2017: 520-529.
[36] PHAM K, KAFLE K, LIN Z, et al. Learning to predict visual attributes in the wild[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2021: 13013-13023.
[37] CHEN K Y, JIANG X L, HU Y, et al. OvarNet: towards open-vocabulary object attribute recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2023: 23518-23527.
[38] LI C L, YANG T, ZHU S J, et al. Density map guided object detection in aerial images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D.C.,USA:IEEE Press,2020: 737-746.
[39] LIU M J, WANG X H, ZHOU A J, et al. UAV-YOLO: small object detection on unmanned aerial vehicle perspective[J]. Sensors, 2020, 20(8): 2238.
[40] LIU W J, QIANG J, LI X X, et al. UAV image small object detection based on composite backbone network[J]. Mobile Information Systems, 2022, 2022: 7319529.
[41] XU C, DING J, WANG J W, et al. Dynamic coarse-to-fine learning for oriented tiny object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2023: 7318-7328.
[42] 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 (CVPR). Washington D.C.,USA:IEEE Press,2022: 13658-13667.
[43] LAI H Q, CHEN L Y, LIU W H, et al. STC-YOLO: small object detection network for traffic signs in complex environments[J]. Sensors, 2023, 23(11): 5307.
[44] 张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312. ZHANG T P, HAN J, LÜ X Q. Super-resolution-aided small-target detection based on multi-task learning[J]. Computer Engineering, 2024, 50(9): 304-312. (in Chinese)
[45] 谢椿辉, 吴金明, 徐怀宇. 改进YOLOv5的无人机影像小目标检测算法[J]. 计算机工程与应用, 2023, 59(9): 198-206. XIE C H, WU J M, XU H Y. Small object detection algorithm based on improved YOLOv5 in UAV image[J]. Computer Engineering and Applications, 2023, 59(9): 198-206. (in Chinese)
[46] TANG S Y, ZHANG S, FANG Y N. HIC-YOLOv5: improved YOLOv5 for small object detection[C]//Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Washington D.C.,USA:IEEE Press,2024: 6614-6619.
[47] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[EB/OL].[2025-04-05]. https://arxiv.org/abs/1807.06521.
[48] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2023: 7464-7475.
[49] SONG G L, LIU Y, WANG X G. Revisiting the sibling head in object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C.,USA:IEEE Press,2020: 11560-11569.
[50] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[EB/OL].[2025-04-05]. https://arxiv.org/abs/1405.0312.
[51] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C.,USA:IEEE Press,2018: 7132-7141.
[52] RUBNER Y, TOMASI C, GUIBAS L J. The Earth mover’s distance as a metric for image retrieval[J]. International Journal of Computer Vision, 2000, 40(2): 99-121.
[53] 石方炎. 人体检测与外观属性识别一体化算法研究[D]. 成都: 电子科技大学, 2020. SHI F Y. Research on integrated algorithm of human detection and appearance attribute recognition[D]. Chengdu: University of Electronic Science and Technology of China, 2020. (in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容