上下文语义表征和像素关系纠正的小样本目标检测

doi:10.11772/j.issn.1001-9081.2024081227

《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (9): 2993-3002.DOI: 10.11772/j.issn.1001-9081.2024081227

• 多媒体计算与计算机仿真 • 上一篇

上下文语义表征和像素关系纠正的小样本目标检测

魏利利¹, 闫丽蓉¹, 唐晓芬¹^,²()

^1.宁夏大学信息工程学院，银川 750021
^2.宁夏“东数西算”人工智能与信息安全重点实验室（宁夏大学），银川 750021

收稿日期:2024-09-02 修回日期:2024-09-30 接受日期:2024-11-04 发布日期:2024-11-19 出版日期:2025-09-10
通讯作者: 唐晓芬
作者简介:魏利利（1996—），女，山东济南人，硕士研究生，CCF会员，主要研究方向：小样本目标检测
闫丽蓉（1999—），女，宁夏中卫人，硕士研究生，CCF会员，主要研究方向：小样本目标检测
基金资助:
国家自然科学基金资助项目(61966029)

Contextual semantic representation and pixel relationship correction for few-shot object detection

Lili WEI¹, Lirong YAN¹, Xiaofen TANG¹^,²()

^1.School of Information Engineering，Ningxia University，Yinchuan Ningxia 750021，China
^2.Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West （Ningxia University），Yinchuan Ningxia 750021，China

Received:2024-09-02 Revised:2024-09-30 Accepted:2024-11-04 Online:2024-11-19 Published:2025-09-10
Contact: Xiaofen TANG
About author:WEI Lili， born in 1996， M. S. candidate. Her research interests include few-shot object detection.
YAN Lirong， born in 1999， M. S. candidate. Her research interests include few-shot object detection.
Supported by:
National Natural Science Foundation of China(61966029)

摘要/Abstract

摘要：

小样本目标检测中因为支持样本稀缺且可利用的类别信息不足，所以有效利用有限样本的特征信息尤为重要。通过丰富支持样本和查询样本中可用的语义信息，能够实现查询特征和支持特征更全面的信息匹配，这有助于模型在小样本场景下理解目标类别，进而有效地实现目标检测。因此，提出一种基于空间上下文和像素关系的模型。设计空间上下文学习模块以辅助像素构建局部上下文区域，从而为中心像素获取区域内的像素语义，并丰富图像的特征信息。此外，针对空间上下文容易引入噪声信息的问题，设计像素上下文关系模块以利用图像中的原始特征知识探索像素之间的关系，并构建类内和类间关系映射图，从而纠正空间上下文学习模块容易引入噪声信息的缺陷。实验结果表明，在PASCAL VOC数据集上进行3种划分时，与VFA（Variational Feature Aggregation）相比，所提模型在样本极其稀缺的1-shot设置下的平均精度（AP₅₀）分别提升2.7、2.0和1.3个百分点。在MS COCO数据集上的10-shot和30-shot设置下，与VFA相比，所提模型的AP分别提升0.4和0.6个百分点；与Meta FR-CNN（Meta Faster R-CNN）相比，所提模型的AP₅₀分别提升11.4和8.7个百分点。可见，所提方法通过更有效地利用有限特征信息提升了对新类样本的识别能力，对只能获取极少量样本的特殊场景下的目标检测模型泛化能力的提升具有参考价值。

关键词: 小样本目标检测, 丰富语义信息, 特征信息匹配, 空间上下文, 像素关系映射

Abstract:

In few-shot object detection， as supporting samples are scarce， and the available class information is insufficient， it is particularly important to utilize feature information of limited samples effectively. By enriching usable semantic information in both supporting and query samples， a more comprehensive matching of information between query features and supporting features can be achieved. This is helpful for the model to understand target class in few-shot scenarios， thereby achieving object detection task effectively. Therefore， a model based on spatial context and pixel relationship was proposed. The spatial context module was designed to assist the pixels in constructing a local context region， thereby obtaining semantics of pixels in the region for the center pixel， and enriching the image feature information. In addition， to address the problem that spatial context introduces noisy information easily， the pixel context relationship module was designed to utilize original feature knowledge in the image to explore relationship between pixels and construct intra- and inter-class relationship maps， so as to correct the defect that spatial context module introduces noisy information easily. Experimental results demonstrate that when PASCAL VOC datasets is divided in three ways， the proposed model has the Average Precision （AP₅₀） improved by 2.7， 2.0， and 1.3 percentage points， respectively， under 1-shot setting where samples are extremely sparse， compared to VFA （Variational Feature Aggregation）； on MS COCO dataset， under 10-shot and 30-shot settings， the proposed model has the AP improved by 0.4 and 0.6 percentage points， respectively， compared to VFA， and the AP₅₀ improved by 11.4 and 8.7 percentage points， respectively， compared to Meta FR-CNN （Meta Faster R-CNN）. It can be seen that the proposed method improves the model’s ability to recognize new classes of samples by using limited feature information more effectively， which has reference value for improving generalization ability of the models in special scenarios where only a very small number of samples can be obtained.

Key words: few-shot object detection, rich semantic information, feature information matching, spatial context, pixel relationship mapping

中图分类号:

TP399

魏利利, 闫丽蓉, 唐晓芬. 上下文语义表征和像素关系纠正的小样本目标检测[J]. 计算机应用, 2025, 45(9): 2993-3002.

Lili WEI, Lirong YAN, Xiaofen TANG. Contextual semantic representation and pixel relationship correction for few-shot object detection[J]. Journal of Computer Applications, 2025, 45(9): 2993-3002.

图/表 15

图1 FSOD任务的划分

Fig. 1 Division of FSOD task

图2 SCM的结构

Fig. 2 Structure of SCM

图3 空间上下文学习模块结构

Fig. 3 Structure of spatial context learning module

图4 像素上下文关系模块结构

Fig. 4 Structure of pixel context relationship module

图5 元学习两阶段训练结构

Fig. 5 Two-stage training structure of meta learning

表1 在VOC数据集上的小样本目标检测性能比较（新类AP50） (%)

Tab. 1 Performance comparison of few-shot object detection on VOC dataset （AP50 for novel classes）

方法	split1					split2					split3
方法	1-shot	2-shot	3-shot	5-shot	10-shot	1-shot	2-shot	3-shot	5-shot	10-shot	1-shot	2-shot	3-shot	5-shot	10-shot
FSCE^［4］	44.2	43.8	51.4	61.9	63.4	27.3	29.5	43.5	44.2	50.2	37.2	41.9	47.5	54.6	58.5
Halluc^［42］	45.1	44.0	44.7	55.0	55.9	23.2	27.5	35.1	34.9	39.0	30.5	35.1	41.4	49.0	49.3
UP-FSOD^［5］	43.8	47.8	50.3	55.4	61.7	31.2	30.5	41.2	42.2	48.3	35.5	39.7	43.9	50.6	53.5
FADI^［9］	50.3	54.8	54.2	59.3	63.2	30.6	35.0	40.3	42.8	48.0	45.7	49.7	49.1	55.0	59.6
DeFRCN^［28］	53.6	57.5	61.5	64.1	60.8	30.1	38.1	47.0	53.3	47.9	48.4	50.9	52.3	54.9	57.4
Meta FR-CNN^［43］	43.0	54.5	60.6	66.1	65.4	27.7	35.5	46.1	47.8	51.4	40.6	46.4	53.4	59.9	58.6
FCT^［21］	49.9	57.1	57.9	63.2	67.1	27.6	34.5	43.7	49.2	51.2	39.5	54.7	52.3	57.0	58.7
KFSOD^［10］	44.6	—	54.4	60.9	65.8	37.8	—	43.1	48.1	50.4	34.8	—	44.1	52.7	53.9
VFA^*［33］	54.4	63.8	64.7	68.0	68.4	40.1	48.9	53.1	52.6	54.5	48.8	57.0	59.2	62.6	63.1
SCM	57.1	64.8	66.3	68.0	68.8	42.1	49.0	52.6	53.1	55.6	50.1	57.8	59.7	62.7	63.5

表2 在COCO数据集上新类的检测性能比较 (%)

Tab. 2 Comparison of detection performance for novel classes on COCO dataset

方法	10-shot			30-shot
方法	AP	$A P 50$	$A P 75$	AP	$A P 50$	$A P 75$
LSTD^［6］	3.2	8.1	2.1	6.7	15.8	5.1
FSRW^［11］	5.6	12.3	4.6	9.1	19.0	7.6
MetaDet^［29］	7.1	14.6	6.1	11.3	21.7	8.1
Meta R-CNN^［44］	8.7	19.1	6.6	12.4	25.3	10.8
TFA w/cos^［26］	10.0	—	9.3	13.7	—	13.4
Attention RPN^［23］	11.1	20.4	10.6	—	—	—
Viewpoint^［45］	12.5	27.3	9.8	14.7	30.6	12.2
MPSR^［32］	9.8	17.9	9.7	14.1	25.4	14.2
CME^［19］	15.1	24.6	16.4	16.9	28.0	17.8
Meta FR-CNN^［43］	12.7	25.7	10.8	16.6	31.8	15.8
VFA^*［33］	16.2	—	—	18.9	—	—
SCM	16.6	37.1	13.2	19.5	40.5	16.9

表2 在COCO数据集上新类的检测性能比较 (%)

Tab. 2 Comparison of detection performance for novel classes on COCO dataset

方法	10-shot			30-shot
方法	AP	$A P 50$	$A P 75$	AP	$A P 50$	$A P 75$
LSTD^［6］	3.2	8.1	2.1	6.7	15.8	5.1
FSRW^［11］	5.6	12.3	4.6	9.1	19.0	7.6
MetaDet^［29］	7.1	14.6	6.1	11.3	21.7	8.1
Meta R-CNN^［44］	8.7	19.1	6.6	12.4	25.3	10.8
TFA w/cos^［26］	10.0	—	9.3	13.7	—	13.4
Attention RPN^［23］	11.1	20.4	10.6	—	—	—
Viewpoint^［45］	12.5	27.3	9.8	14.7	30.6	12.2
MPSR^［32］	9.8	17.9	9.7	14.1	25.4	14.2
CME^［19］	15.1	24.6	16.4	16.9	28.0	17.8
Meta FR-CNN^［43］	12.7	25.7	10.8	16.6	31.8	15.8
VFA^*［33］	16.2	—	—	18.9	—	—
SCM	16.6	37.1	13.2	19.5	40.5	16.9

表3 在模型不同训练阶段加入先验空间上下文方法的AP50比较 (%)

Tab. 3 Comparison of AP50 of adding prior spatial context method at different model training stages

划分	阶段	1-shot	2-shot	3-shot	5-shot	10-shot
split1	基础训练	53.9	64.1	65.2	67.3	68.6
split1	微调训练	57.1	64.8	66.3	68.0	68.8
split2	基础训练	37.7	46.8	50.2	49.2	52.6
split2	微调训练	42.1	49.0	52.6	53.1	55.6
split3	基础训练	51.1	54.6	58.6	61.7	62.7
split3	微调训练	50.1	57.8	59.7	62.7	63.5

表4 模型各组件的影响（AP50） (%)

Tab. 4 Influence of different model components （AP50）

组件	SCL-Q	SCL-S	PCR	1-shot	2-shot	3-shot	5-shot	10-shot
VFA				54.4	63.8	64.7	68.0	68.4
SCM	√			55.6	64.2	65.0	68.5	68.6
		√		55.7	64.3	64.6	68.2	68.3
			√	56.3	64.1	64.9	68.3	68.5
	√	√		55.7	64.2	65.0	68.5	68.6
		√	√	56.7	64.5	65.8	68.3	68.6
	√	√	√	57.1	64.8	66.3	68.0	68.8

表5 SCL模块中不同空间范围选择的结果对比（AP50） (%)

Tab. 5 Comparison results of selecting different spatial ranges in SCL module （AP50）

分支	范围选择	1-shot	2-shot	3-shot	5-shot	10-shot
查询分支	Q：9	53.4	63.2	64.8	67.8	68.7
	Q：11	54.5	63.0	64.7	67.9	68.2
	Q：13	54.1	63.6	64.9	68.4	68.1
	Q：15	55.1	63.4	64.9	68.8	69.0
支持分支	S：5	54.1	62.9	65.0	67.9	68.1
	S：7	52.1	62.3	64.5	67.7	67.9
	S：9	53.5	63.3	64.5	68.2	68.2
双分支	Q：11，S：5	55.7	63.7	64.6	68.3	68.1
	Q：11，S：7	54.1	63.5	64.8	67.8	68.7
	Q：11，S：9	57.1	64.9	66.2	68.1	68.5
	Q：11，S：11	56.4	64.5	65.1	67.8	68.4
	Q：13，S：5	55.3	64.0	64.8	67.7	68.4
	Q：13，S：7	55.3	63.4	64.2	67.5	68.3
	Q：13，S：9	55.0	63.5	64.9	69.0	68.2

表6 1-shot设置下的基类精度对比 (%)

Tab. 6 Comparison of base class precision under 1-shot setting

类别	VFA	SCM	类别	VFA	SCM
bicycle	78.4	81.4	diningtable	40.4	48.2
car	76.7	79.4	horse	83.9	84.2
boat	66.3	67.1	sheep	75.2	76.1
cat	86.1	87.2	tvmonitor	52.2	56.0
chair	10.8	18.6

表7 1-shot设置下的新类精度对比 (%)

Tab. 7 Comparison of novel class precision under 1-shot setting

类别	VFA	SCM	类别	VFA	SCM
bird	47.2	49.2	motorbike	69.2	70.6
bus	62.2	63.1	sofa	37.5	40.0
cow	59.0	62.5

表8 不同特征的像素上下文关系计算的AP50对比 (%)

Tab. 8 Comparison of AP50 for pixel context relationships with different features

特征	1-shot	2-shot	3-shot	4-shot	5-shot
Context Feature	56.4	64.3	66.3	68.3	68.6
Initial Feature	57.1	64.8	66.3	68.0	68.8

图6 特征图的可视化

Fig. 6 Visualization of feature maps

图7 小样本检测结果的可视化

Fig. 7 Visualization of few-shot object detection results

参考文献 45

[1]	ZHANG Y， WEI X S， ZHOU B， et al. Bag of tricks for long-tailed visual recognition with deep convolutional neural networks ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 3447-3455.
[2]	WANG C， LI Z， MO X， et al. Exploiting unfairness with meta-Set learning for chronological age estimation ［J］. IEEE Transactions on Information Forensics and Security， 2023， 18： 5678-5690.
[3]	史燕燕，史殿习，乔子腾，等. 小样本目标检测研究综述［J］. 计算机学报， 2023， 46（8）： 1753-1780.
	SHI Y Y， SHI D X， QIAO Z T， et al. A survey on recent advances in few-shot object detection［J］. Chinese Journal of Computers， 2023， 46（8）： 1753-1780.
[4]	SUN B， LI B， CAI S， et al. FSCE： few-shot object detection via contrastive proposal encoding ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 7348-7358.
[5]	WU A， HAN Y， ZHU L， et al. Universal-prototype enhancing for few-shot object detection ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 9547-9556.
[6]	CHEN H， WANG Y， WANG G， et al. LSTD： a low-shot transfer detector for object detection ［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2018： 2836-2843.
[7]	SHANGGUAN Z， SEITA D， ROSTAMI M. Cross-domain multi-modal few-shot object detection via rich text ［C］// Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway： IEEE， 2025： 6570-6580.
[8]	FU Y， WANG Y， PAN Y， et al. Cross-domain few-shot object detection via enhanced open-set object detector ［C］// Proceedings of the 2024 European Conference on Computer Vision， LNCS 15116. Cham： Springer， 2025： 247-264.
[9]	CAO Y， WANG J， JIN Y， et al. Few-shot object detection via association and discrimination ［C］// Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2021： 16570-16581.
[10]	ZHANG S， WANG L， MURRAY N， et al. Kernelized few-shot object detection with efficient integral aggregation ［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 19185-19194.
[11]	KANG B， LIU Z， WANG X， et al. Few-shot object detection via feature reweighting ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 8419-8428.
[12]	李鸿天，史鑫昊，潘卫国，等. 融合多尺度和注意力机制的小样本目标检测［J］.计算机应用， 2024， 44（5）：1437-1444.
	LI H T， SHI X H， PAN W G， et al. Few-shot object detection via fusing multi-scale and attention mechanism ［J］. Journal of Computer Applications， 2024， 44（5）：1437-1444.
[13]	CHEN T I， LIU Y C， SU H T， et al. Dual-awareness attention for few-shot object detection ［J］. IEEE Transactions on Multimedia， 2023， 25： 291-301.
[14]	LI B， WANG C， REDDY P， et al. AirDet： few-shot detection without fine-tuning for autonomous exploration ［C］// Proceedings of the 2022 European Conference on Computer Vision， LNCS 13699. Cham： Springer， 2022： 427-444.
[15]	ZHANG X， CHEN Z， ZHANG J， et al. Learning general and specific embedding with Transformer for few-shot object detection［J］. International Journal of Computer Vision， 2025， 133（2）： 968-984.
[16]	LI W， ZHOU J， LI X， et al. InfRS： incremental few-shot object detection in remote sensing images ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： No.5644314.
[17]	MA J， NIU Y， XU J， et al. DiGeo： discriminative geometry-aware learning for generalized few-shot object detection ［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2023： 3208-3218.
[18]	CHEN H， WANG Q， XIE K， et al. MPF-Net： multi-projection filtering network for few-shot object detection ［J］. Applied Intelligence， 2024， 54（17/18）： 7777-7792.
[19]	LI B， YANG B， LIU C， et al. Beyond max-margin： class margin equilibrium for few-shot object detection ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 7359-7368.
[20]	李新叶，侯晔凝，孔英会，等. 结合特征融合与增强注意力的少样本目标检测［J］. 计算机应用， 2024， 44（3）：745-751.
	LI X Y， HOU Y N， KONG Y H， et al. Few-shot object detection combining feature fusion and enhanced attention ［J］. Journal of Computer Applications， 2024， 44（3）：745-751.
[21]	HAN G， MA J， HUANG S， et al. Few-shot object detection with fully cross-Transformer ［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 5321-5330.
[22]	CARION N， MASSA F， SYNNAEVE G， et al. End-to-end object detection with Transformers ［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12346. Cham： Springer， 2020： 213-229.
[23]	FAN Q， ZHUO W， TANG C K， et al. Few-shot object detection with attention-RPN and multi-relation detector ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 4012-4021.
[24]	SHANGGUAN Z， ROSTAMI M. Improved region proposal network for enhanced few-shot object detection ［J］. Neural Networks， 2024， 180： No.106699.
[25]	CHOI T M， KIM J H. Incremental few-shot object detection via simple fine-tuning approach ［C］// Proceedings of the 2023 IEEE International Conference on Robotics and Automation. Piscataway： IEEE， 2023： 9289-9295.
[26]	WANG X， HUANG T E， DARRELL T， et al. Frustratingly simple few-shot object detection ［C］// Proceedings of the 37th International Conference on Machine Learning. New York： JMLR.org， 2020： 9919-9928.
[27]	HU H， BAI S， LI A， et al. Dense relation distillation with context-aware aggregation for few-shot object detection ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 10180-10189.
[28]	QIAO L， ZHAO Y， LI Z， et al. DeFRCN： decoupled Faster R-CNN for few-shot object detection ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2021： 8661-8670.
[29]	WANG Y X， RAMANAN D， HEBERT M. Meta-learning to detect rare objects ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 9924-9933.
[30]	ZHANG G， LUO Z， CUI K， et al. Meta-DETR： image-level few-shot object detection with inter-class correlation exploitation ［J］. Neural Networks， 2023， 45（11）： 12832-12843.
[31]	ZHU X， SU W， LU L， et al. Deformable DETR： deformable Transformers for end-to-end object detection ［EB/OL］. ［2024-05-18］. .
[32]	WU J， LIU S， HUANG D， et al. Multi-scale positive sample refinement for few-shot object detection ［C］// Proceedings of the 2020 European Conference on Computer Vision， LNCS 12361. Cham： Springer， 2020： 456-472.
[33]	HAN J， REN Y， DING J， et al. Few-shot object detection via variational feature aggregation ［C］// Proceedings of the 37th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2023： 755-763.
[34]	KINGMA D P， WELLING M. Auto-encoding variational Bayes［EB/OL］. ［2024-05-24］. .
[35]	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks ［C］// Proceedings of the 28th International Conference on Neural Information Processing Systems — Volume 1. Cambridge： MIT Press， 2015： 91-99.
[36]	WANG Z， YANG B， YUE H， et al. Fine-grained prototypes distillation for few-shot object detection ［C］// Proceedings of the 38th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2024： 5859-5866.
[37]	EVERINGHAM M， VAN GOOL L， WILLIAMS C K I， et al. The PASCAL Visual Object Classes （VOC） challenge ［J］. International Journal of Computer Vision， 2010， 88（2）： 303-338.
[38]	CHEN X， FANG H， LIN T Y， et al. Microsoft COCO captions： data collection and evaluation server ［EB/OL］. ［2024-05-21］..
[39]	OpenMMLab. OpenMMLab few shot learning toolbox and benchmark ［EB/OL］. ［2024-06-18］..
[40]	DENG J， DONG W， SOCHER R， et al. ImageNet： a large-scale hierarchical image database ［C］// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2009： 248-255.
[41]	HE K， ZHANG X， REN S， et al. Deep residual learning for image recognition ［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 770-778.
[42]	ZHANG W， WANG Y X. Hallucination improves few-shot object detection ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2021： 13003-13012.
[43]	HAN G， HUANG S， MA J， et al. Meta Faster R-CNN： towards accurate few-shot object detection with attentive feature alignment［C］// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2022： 780-789.
[44]	YAN X， CHEN Z， XU A， et al. Meta R-CNN： towards general solver for instance-level low-shot learning ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 9576-9585.
[45]	XIAO Y， LEPETIT V， MARLET R. Few-shot object detection and Viewpoint estimation for objects in the wild ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（3）： 3090-3106.

上下文语义表征和像素关系纠正的小样本目标检测

Contextual semantic representation and pixel relationship correction for few-shot object detection

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 45

相关文章 4

编辑推荐

Metrics

[1]	张嘉祥, 李晓明, 张佳慧. 结合新类特征增强与度量机制的小样本目标检测算法[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2984-2992.
[2]	李鸿天, 史鑫昊, 潘卫国, 徐成, 徐冰心, 袁家政. 融合多尺度和注意力机制的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1437-1444.
[3]	付可意, 王高才, 邬满. 基于改进区域提议网络和特征聚合小样本目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3790-3797.
[4]	林润超, 黄荣, 董爱华. 基于注意力机制和元特征二次重加权的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2022, 42(10): 3025-3032.