Few‑shot target detection based on negative‑margin loss

doi:10.11772/j.issn.1001-9081.2021091683

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (11): 3617-3624.DOI: 10.11772/j.issn.1001-9081.2021091683

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Few‑shot target detection based on negative‑margin loss

Yunyan DU¹^,², Hong LI¹^,², Jinhui YANG¹^,², Yu JIANG¹^,², Yao MAO¹^,²()

^1.University of Chinese Academy of Sciences，Beijing 100049，China
^2.Key Laboratory of Optical Engineering，Chinese Academy of Sciences （Institute of Optics and Electronics），Chengdu Sichuan 610207，China

Received:2021-09-27 Revised:2022-05-25 Accepted:2022-05-26 Online:2022-11-14 Published:2022-11-10
Contact: Yao MAO
About author:DU Yunyan， born in 1997， M. S. candidate. Her research interests include target detection， few-shot learning.
LI Hong， born in 1996， M. S. candidate. His research interests include deep learning， lightweight target detection.
YANG Jinhui， born in 1996， M. S. candidate. His research interests include lightweight target detection.
JIANG Yu， born in 1977， M. S.， associate researcher. Her research interests include computer application technology， human computer interaction system.
MAO Yao， born in 1978， Ph. D.， researcher. His research interests include computer technology， machine vision， reinforcement learning.
Supported by:
The National Key Research and Development Program of China(2017YFB1103002)

基于负边距损失的小样本目标检测

杜芸彦¹^,², 李鸿¹^,², 杨锦辉¹^,², 江彧¹^,², 毛耀¹^,²()

^1.中国科学院大学，北京 100049
^2.中国科学院光束控制重点实验室（中国科学院光电技术研究所），成都 610207

通讯作者: 毛耀
作者简介:杜芸彦（1997—），女，四川成都人，硕士研究生，主要研究方向：目标检测、小样本学习
李鸿（1996—），男，贵州毕节人，硕士研究生，主要研究方向：深度学习、轻量化目标检测
杨锦辉（1996—），男，甘肃平凉人，硕士研究生，主要研究方向：轻量化目标检测
江彧（1977—），女，安徽黄山人，副研究员，硕士，主要研究方向：人机交互系统
毛耀（1978—），男，四川眉山人，研究员，博士，CCF会员，主要研究方向：机器视觉、强化学习。maoyao@ioe.ac.cn
基金资助:
国家重点研发计划项目(2017YFB1103002)

Abstract

Abstract:

Most of the existing target detection algorithms rely on large?scale annotation datasets to ensure the accuracy of detection， however， it is difficult for some scenes to obtain a large number of annotation data and it consums a lot of human and material resources. In order to resolve this problem， a Few?Shot Target Detection method based on Negative Margin loss （NM?FSTD） was proposed. The negative margin loss method belonging to metric learning in Few?Shot Learning （FSL） was introduced into target detection， which could avoid mistakenly mapping the samples of the same novel classes to multiple peaks or clusters and helping to the classification of novel classes in few?shot target detection. Firstly， a large number of training samples and the target detection framework based on negative margin loss were used to train the model with good generalization performance. Then， the model was finetuned through a small number of labeled target category samples. Finally， the finetuned model was used to detect the new sample of target category. To verify the detection effect of NM?FSTD， MS COCO was used for training and evaluation. Experimental results show that the AP₅₀ of NM?FSTD reaches 22.8%； compared with Meta R?CNN （Meta Regions with CNN features） and MPSR （Multi?Scale Positive Sample Refinement）， the accuracies are improved by 3.7 and 4.9 percentage points， respectively. NM?FSTD can effectively improve the detection performance of target categories in the case of few?shot， and solve the problem of insufficient data in the field of target detection.

Key words: target detection, Few?Shot Learning (FSL), negative?margin loss, metric learning

摘要：

现有的大部分目标检测算法都依赖于大规模的标注数据集来保证检测的正确率，但某些场景往往很难获得大量标注数据，且耗费大量人力、物力。针对这一问题，提出了基于负边距损失的小样本目标检测方法（NM?FSTD），将小样本学习（FSL）中属于度量学习的负边距损失方法引入目标检测，负边距损失可以避免将同一新类的样本错误地映射到多个峰值或簇，有助于小样本目标检测中新类的分类。首先采用大量训练样本和基于负边距损失的目标检测框架训练得到具有良好泛化性能的模型，之后通过少量具有标签的目标类别的样本对模型进行微调，并采用微调后的模型对目标类别的新样本进行目标检测。为了验证NM?FSTD的检测效果，使用MS COCO进行训练和评估。实验结果表明，所提方法AP₅₀达到了22.8%，与Meta R?CNN和MPSR相比，准确率分别提高了3.7和4.9个百分点。NM?FSTD能有效提高在小样本情况下对目标类别的检测性能，解决目前目标检测领域中数据不足的问题。

关键词: 目标检测, 小样本学习, 负边距损失, 度量学习

CLC Number:

TP391.41

Yunyan DU, Hong LI, Jinhui YANG, Yu JIANG, Yao MAO. Few‑shot target detection based on negative‑margin loss[J]. Journal of Computer Applications, 2022, 42(11): 3617-3624.

杜芸彦, 李鸿, 杨锦辉, 江彧, 毛耀. 基于负边距损失的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2022, 42(11): 3617-3624.

Figures/Tables 10

Fig. 1 Overall structure of FSOD model

Fig. 2 Overall framework of NM?FSTD

Fig. 3 Calculation process of Neg?Mar Softmax Loss and Neg?Mar Cos?Softmax Loss

Tab. 1 Classification accuracy comparison of Cosine Softmax loss with different m on miniImagenet dataset

$m$	$A c c t r a$	1‑shot val	5‑shot val	1‑shot test	5‑shot test
-0.15	70.63	57.02 $±$ 0.83	77.26 $±$ 0.66	56.33 $±$ 0.77	76.20 $±$ 0.63
-0.10	80.96	61.93 $±$ 0.84	80.61 $±$ 0.57	60.90 $±$ 0.81	79.14 $±$ 0.61
-0.05	86.93	64.86 $±$ 0.83	81.97 $±$ 0.57	61.89 $±$ 0.81	80.43 $±$ 0.57
-0.02	89.15	66.13 $±$ 0.82	82.81 $±$ 0.55	62.43 $±$ 0.82	80.94 $±$ 0.56
0	90.43	65.79 $±$ 0.85	83.24 $±$ 0.55	60.98 $±$ 0.80	80.13 $±$ 0.57
0.02	90.96	66.83 $±$ 0.86	83.68 $±$ 0.53	61.69 $±$ 0.83	79.53 $±$ 0.61
0.05	91.89	66.27 $±$ 0.87	83.83 $±$ 0.55	61.05 $±$ 0.81	79.21 $±$ 0.60
0.10	90.37	65.55 $±$ 0.91	82.16 $±$ 0.55	59.24 $±$ 0.85	77.53 $±$ 0.66
0.20	91.98	63.08 $±$ 0.93	79.59 $±$ 0.64	56.44 $±$ 0.80	74.75 $±$ 0.65

Tab. 1 Classification accuracy comparison of Cosine Softmax loss with different m on miniImagenet dataset

$m$	$A c c t r a$	1‑shot val	5‑shot val	1‑shot test	5‑shot test
-0.15	70.63	57.02 $±$ 0.83	77.26 $±$ 0.66	56.33 $±$ 0.77	76.20 $±$ 0.63
-0.10	80.96	61.93 $±$ 0.84	80.61 $±$ 0.57	60.90 $±$ 0.81	79.14 $±$ 0.61
-0.05	86.93	64.86 $±$ 0.83	81.97 $±$ 0.57	61.89 $±$ 0.81	80.43 $±$ 0.57
-0.02	89.15	66.13 $±$ 0.82	82.81 $±$ 0.55	62.43 $±$ 0.82	80.94 $±$ 0.56
0	90.43	65.79 $±$ 0.85	83.24 $±$ 0.55	60.98 $±$ 0.80	80.13 $±$ 0.57
0.02	90.96	66.83 $±$ 0.86	83.68 $±$ 0.53	61.69 $±$ 0.83	79.53 $±$ 0.61
0.05	91.89	66.27 $±$ 0.87	83.83 $±$ 0.55	61.05 $±$ 0.81	79.21 $±$ 0.60
0.10	90.37	65.55 $±$ 0.91	82.16 $±$ 0.55	59.24 $±$ 0.85	77.53 $±$ 0.66
0.20	91.98	63.08 $±$ 0.93	79.59 $±$ 0.64	56.44 $±$ 0.80	74.75 $±$ 0.65

Tab. 2 Classification accuracy comparison of Softmax loss with different m on miniImagenet dataset

$m$	$A c c t r a$	1‑shot val	5‑shot val	1‑shot test	5‑shot test
-0.8	81.79	59.45 $±$ 0.84	78.02 $±$ 0.59	57.76 $±$ 0.82	77.14 $±$ 0.60
-0.5	88.82	59.03 $±$ 0.80	79.25 $±$ 0.55	58.46 $±$ 0.83	78.24 $±$ 0.61
-0.3	92.68	59.14 $±$ 0.89	79.40 $±$ 0.58	59.02 $±$ 0.81	78.80 $±$ 0.61
0	93.22	58.83 $±$ 0.86	79.34 $±$ 0.55	56.87 $±$ 0.78	77.97 $±$ 0.57
0.3	92.61	59.27 $±$ 0.83	80.26 $±$ 0.57	57.41 $±$ 0.79	78.40 $±$ 0.59
0.5	88.78	58.90 $±$ 0.89	78.61 $±$ 0.61	57.54 $±$ 0.81	77.44 $±$ 0.63
0.8	93.94	58.50 $±$ 0.87	79.41 $±$ 0.58	56.36 $±$ 0.79	77.87 $±$ 0.56

Tab. 2 Classification accuracy comparison of Softmax loss with different m on miniImagenet dataset

$m$	$A c c t r a$	1‑shot val	5‑shot val	1‑shot test	5‑shot test
-0.8	81.79	59.45 $±$ 0.84	78.02 $±$ 0.59	57.76 $±$ 0.82	77.14 $±$ 0.60
-0.5	88.82	59.03 $±$ 0.80	79.25 $±$ 0.55	58.46 $±$ 0.83	78.24 $±$ 0.61
-0.3	92.68	59.14 $±$ 0.89	79.40 $±$ 0.58	59.02 $±$ 0.81	78.80 $±$ 0.61
0	93.22	58.83 $±$ 0.86	79.34 $±$ 0.55	56.87 $±$ 0.78	77.97 $±$ 0.57
0.3	92.61	59.27 $±$ 0.83	80.26 $±$ 0.57	57.41 $±$ 0.79	78.40 $±$ 0.59
0.5	88.78	58.90 $±$ 0.89	78.61 $±$ 0.61	57.54 $±$ 0.81	77.44 $±$ 0.63
0.8	93.94	58.50 $±$ 0.87	79.41 $±$ 0.58	56.36 $±$ 0.79	77.87 $±$ 0.56

Tab.3 Performance comparison of different methods

方法	Backbone	AP/%	AP₅₀/%	AP₇₅/%	参数量/10⁶	FLOPs/10⁹
LSTD	VGG‑16	3.2	—	—	138.36	15.5
FR	DarkNet‑19	5.6	12.3	4.6	20.83	15.5
Meta R‑CNN	ResNet‑101	8.7	19.1	6.6	44.55	7.85
MPSR		9.8	17.9	9.7
TFA		10.0	—	9.3
SRR‑FSD		11.3	23.0	9.8
FSCE		11.9	—	10.5
FSOD	ResNet‑50	11.1	20.4	10.6	25.56	4.12
Cos‑FSOD		10.3	20.2	9.2
Neg‑Mar Softmax FSTD（本文方法）		10.9	21.4	10.1
Neg‑Mar Cos‑Softmax FSTD （本文方法）		12.2	22.8	11.7

Tab. 4 Influence of negative margin loss on accuracy in few?shot target detection

算法	负边距损失	AP	AP₅₀	AP₇₅	AP_S	AP_M	AP_L
FSOD（Ours Impl）		10.7	20.1	10.0	2.2	11.6	17.8
Neg‑Mar Softmax FSTD（Ours）	√	10.9	21.4	10.1	3.5	12.4	19.2
Cos‑FSOD（Ours Impl）		10.3	20.2	9.2	2.2	11.5	17.7
Neg‑Mar Cos‑Softmax FSTD （Ours）	√	12.2	22.8	11.7	3.6	12.4	20.9

Tab. 5 Ablation experimental results of backbone networks unit： %

Backbone	AP	AP₅₀	AP₇₅
ResNet‑34	9.4	19.5	8.7
ResNet‑50	12.2	22.8	11.7
ResNet‑101	14.0	24.3	13.4

Fig.4 Detection results of NM?FSTD on train classes

Fig.5 Detection results of NM?FSTD on novel classes

References 50

1	LIU W， ANGUELOY D， ERHAN D， et al. SSD： Single Shot MultiBox Detector［C］// Proceedings of the 2016 European Conference on Computer Vision， LNIP 9905. Cham： Springer， 2016： 21-37.
2	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real‑time object detection［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 779-788. 10.1109/cvpr.2016.91
3	REDMON J， FARHADI A. YOLO9000： better， faster， stronger［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 6517-6525. 10.1109/cvpr.2017.690
4	REDMON J， FARHADI A. YOLOv3： an incremental improvement ［EB/OL］. ［2021-08-10］. .
5	BOCHKOVSKIY A， WANG C Y， LIAO H. YOLOv4： optimal speed and accuracy of object detection ［EB/OL］. ［2021-07-05］. .
6	刘丹，吴亚娟，罗南超，等. 嵌入注意力和特征交织模块的Gaussian‑YOLO v3目标检测［J］. 计算机应用， 2020， 40（8）： 2225-2230.
	LIU D， WU Y J， LUO N C， et al. Object detection of Gaussian‑YOLO v3 implanting attention and feature intertwine modules［J］. Journal of Computer Applications， 2020， 40（8）： 2225-2230.
7	HE K， ZHANG X， REN S， et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014， 37（9）：1904-1916. 10.1109/tpami.2015.2389824
8	GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2014： 580-587. 10.1109/cvpr.2014.81
9	GIRSHICK R. Fast RCNN［C］// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2015： 1440-1448. 10.1109/iccv.2015.169
10	REN S， HE K， 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. 10.1109/tpami.2016.2577031
11	WANG Y， YAO Q， KWOK J T， et al. Generalizing from a few examples： a survey on few‑shot learning［J］. ACM Computing Surveys， 2020， 53（3）：1-34. 10.1145/3386252
12	MILLER E G， MATSAKIS N E， VIOLA P A. Learning from one example through shared densities on transforms［C］// Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2000： 464-471. 10.1109/cvpr.2000.855790
13	SCHWARTZ E， KARLINSKY L， SHTOK J， et al. Delta‑ encoder： an effective sample synthesis method for few‑shot object recognition［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 2850-2860.
14	甘岚，沈鸿飞，王瑶，等. 基于改进DCGAN的数据增强方法［J］. 计算机应用， 2021， 41（5）： 1305-1313.
	GAN L， SHEN H F， WANG Y， et al. Data augmentation method based on improved deep convolutional generative adversarial networks［J］. Journal of Computer Applications， 2021， 41（5）： 1305-1313.
15	陈佛计，朱枫，吴清潇，等. 基于生成对抗网络的红外图像数据增强［J］. 计算机应用， 2020， 40（7）： 2084-2088.
	CHEN F J， ZHU F， WU Q X， et al. Infrared image data augmentation based on generative adversarial network［J］. Journal of Computer Applications， 2020， 40（7）： 2084-2088.
16	HARIHARAN B， GIRSHICK R. Low‑shot visual recognition by shrinking and hallucinating features［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 3037-3046. 10.1109/iccv.2017.328
17	PFISTER T， CHARLES J， ZISSERMAN A. Domain‑adaptive discriminative one‑shot learning of gestures［C］// Proceedings of the 2014 European Conference on Computer Vision， LNCS 8694. Cham： Springer， 2014： 814-829.
18	DOUZE M， SZLAM A， HARIHARAN B， et al. Low‑shot learning with large‑scale diffusion［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington， DC： IEEE Computer Society， 2018： 3349-3358. 10.1109/cvpr.2018.00353
19	GRANT E， FINN C， LEVINE S， et al. Recasting gradient‑based meta‑learning as hierarchical Bayes ［EB/OL］. ［2021-08-10］. .
20	TSAI Y， SALAKHUTDINOV R. Improving one‑shot learning through fusing side information ［EB/OL］. ［2021-06-19］. .
21	GAO H， SHOU Z， ZAREIAN A， et al. Low‑shot learning via covariance‑preserving adversarial augmentation networks［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2018： 983-993.
22	VINYALS O， BLUNDELL C， LILLICRAP T， et al. Matching networks for one shot learning［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2016： 3637-3645.
23	SNELL J， SWERSKY K， ZEMEL R S. Prototypical networks for few‑shot learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 4077-4087.
24	SUNG F， YANG Y， ZHANG L， et al. Learning to compare： relation network for few‑shot learning［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 1199-1208. 10.1109/cvpr.2018.00131
25	KOCH G R， ZEMEL R， SALAKHUTDINOV R. Siamese neural networks for one‑shot image recognition［C/OL］// Proceedings of the 2015 32nd International Conference on Machine Learning. Brookline， MA： JMLR.org， 2015 ［2021-06-05］. .
26	MUNKHDALAI T， YU H. Meta networks［C］// Proceedings of the 34th International Conference on Machine Learning. Brookline， MA： JMLR.org， 2017： 2554-2563.
27	LAKE B M， SALAKHUTDINOV R， TENENBAUM J B. Human‑ level concept learning through probabilistic program induction［J］. Science， 2015， 350（6266）： 1332-1338. 10.1126/science.aab3050
28	KINGMA D P， WELLING M. Auto‑encoding variational Bayes ［EB/OL］. ［2021-07-10］. .
29	HOFFMAN J， TZENG E， DONAHUE J， et al. One‑shot adaptation of supervised deep convolutional models ［EB/OL］. ［2021-06-15］. .
30	LEE Y， CHOI S. Gradient‑based meta‑learning with learned layerwise metric and subspace ［EB/OL］. ［2021-05-10］. .
31	潘兴甲，张旭龙，董未名，等.小样本目标检测的研究现状［J］.南京信息工程大学学报（自然科学版），2019，11（6）：698-705.
	PAN X J， ZHANG X L， DONG W M， et al. A survey of few‑shot object detection［J］. Journal of Nanjing University of Information Science and Technology （Natural Science Edition）， 2019，11（6）：698-705
32	CHEN H， WANG Y， WANG G， et al. LSTD： a low‑shot transfer detector for object detection ［EB/OL］. ［2021-04-25］. .
33	SINGH P， VARADARAJAN S， SINGH A N， et al. Multidomain document layout understanding using few shot object detection ［EB/OL］. ［2021-05-10］. .
34	ZHANG T， ZHANG Y， SUN X， et al. Comparison network for one‑shot conditional object detection ［EB/OL］. ［2021-08-10］. .
35	KARLINSKY L， SHTOK J， HARARY S， et al. RepMet： representative‑based metric learning for classification and few‑shot object detection［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Washington， DC： IEEE Computer Society， 2019： 5192-5201. 10.1109/cvpr.2019.00534
36	SUN B， LI B， CAI S， et al. FSCE： Few‑shot object detection via contrastive proposal encoding［C］// Proceedings of the 2021 IEEE Conference on Computer Vision and Pattern Recognition. Washington， DC： IEEE Computer Society， 2021： 7352-7362. 10.1109/cvpr46437.2021.00727
37	FU K， ZHANG T， ZHANG Y， et al. Meta‑SSD： towards fast adaptation for few‑shot object detection with meta‑learning［J］. IEEE Access， 2019， 7： 77597-77606. 10.1109/access.2019.2922438
38	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. Washington， DC： IEEE Computer Society， 2020：4012-4021. 10.1109/cvpr42600.2020.00407
39	WEN Y， ZHANG K， LI Z， et al. A discriminative feature learning approach for deep face recognition［C］// Proceedings of the 2016 European Conference on Computer Vision， LNIP 9911. Cham： Springer， 2016： 499-512.
40	LIU W， WEN Y， YU Z， et al. Large‑margin Softmax loss for convolutional neural networks ［EB/OL］. ［2021-07-01］. .
41	DENG J， GUO J， ZAFEIRIOU S. ArcFace： additive angular margin loss for deep face recognition ［EB/OL］. ［2021-05-17］. .
42	WANG H， WANG Y， ZHOU Z， et al. CosFace： large margin cosine loss for deep face recognition［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington， DC： IEEE Computer Society， 2018： 5265-5274. 10.1109/cvpr.2018.00552
43	LIU B， CAO Y， LIN Y， et al. Negative margin matters： understanding margin in few‑shot classification ［C］// Proceedings of the 2020 European Conference on Computer Vision， LNIP 12361. Cham： Springer， 2020： 438-455.
44	LIU W， WEN Y， YU Z， et al. SphereFace： deep hypersphere embedding for face recognition［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington， DC： IEEE Computer Society， 2017： 6738-6746. 10.1109/cvpr.2017.713
45	LIN T Y， MAIRE M， BELONGIE S， et al. Microsoft COCO： common objects in context［C］// Proceedings of the 2014 European Conference on Computer Vision， LNIP 8693. Cham： Springer， 2014： 740-755.
46	KANG B， ZHUANG L， XIN W， et al. Few‑shot object detection via feature reweighting［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 8420-8429. 10.1109/iccv.2019.00851
47	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. 10.1109/iccv.2019.00967
48	ZHU C， CHEN F， AHMED U， et al. Semantic relation reasoning for shot‑stable few‑shot object detection ［EB/OL］. ［2021-08-05］. .
49	WANG X， HUANG T E， DARRELL T， et al. Frustratingly simple few-shot object detection ［EB/OL］. ［2021-08-10］. .
50	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， LNIP 12361. Cham： Springer， 2020： 456-472.

[1]	Zhangjian JI, Na DU. Tiny target detection based on improved VariFocalNet [J]. Journal of Computer Applications, 2024, 44(7): 2200-2207.
[2]	Tianhua CHEN, Jiaxuan ZHU, Jie YIN. Bird recognition algorithm based on attention mechanism [J]. Journal of Computer Applications, 2024, 44(4): 1114-1120.
[3]	Zhanjun JIANG, Baijing WU, Long MA, Jing LIAN. Faster-RCNN water-floating garbage recognition based on multi-scale feature and polarized self-attention [J]. Journal of Computer Applications, 2024, 44(3): 938-944.
[4]	Yuliang ZHENG, Yunhua CHEN, Weijie BAI, Pinghua CHEN. Vehicle target detection by fusing event data and image frames [J]. Journal of Computer Applications, 2024, 44(3): 931-937.
[5]	Cunyi LIAO, Yi ZHENG, Weijin LIU, Huan YU, Shouyin LIU. Decoupling-fusing algorithm for multiple tasks with autonomous driving environment perception [J]. Journal of Computer Applications, 2024, 44(2): 424-431.
[6]	Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929.
[7]	Lin WANG, Jingliang LIU, Wuwei WANG. Small target detection method in UAV images based on fusion of dilated convolution and Transformer [J]. Journal of Computer Applications, 2024, 44(11): 3595-3602.
[8]	Dahai LI, Bingtao LI, Zhendong WANG. Underwater target detection algorithm based on improved YOLOv8 [J]. Journal of Computer Applications, 2024, 44(11): 3610-3616.
[9]	Wenze CHAI, Jing FAN, Shukui SUN, Yiming LIANG, Jingfeng LIU. Overview of deep metric learning [J]. Journal of Computer Applications, 2024, 44(10): 2995-3010.
[10]	Meijia LIANG, Xinwu LIU, Xiaopeng HU. Small target detection algorithm for train operating environment image based on improved YOLOv3 [J]. Journal of Computer Applications, 2023, 43(8): 2611-2618.
[11]	Haifeng LI, Fan ZHANG, Minnan PIAO, Huaichao WANG, Nansha LI, Zhongcheng GUI. Automatic detection of targets under airport pavement based on channel and spatial attention [J]. Journal of Computer Applications, 2023, 43(3): 930-935.
[12]	CHEN Haiyan, JIA Mingming, ZHAO Wenli, WANG Chanfei. Target detection of Ochotona curzoniae based on embedded Jetson TX2 [J]. Journal of Computer Applications, 2023, 43(1): 98-103.
[13]	LI Kewen, YANG Jiantao, HUANG Zongchao. Improved YOLOv3 target detection based on boundary limit point features [J]. Journal of Computer Applications, 2023, 43(1): 81-87.
[14]	Zhihong XI, Jiaxu WEN. Indoor dynamic scene localization and mapping based on target detection [J]. Journal of Computer Applications, 2022, 42(9): 2853-2857.
[15]	Shiwen ZHANG, Chunhua DENG, Junwen ZHANG. Application of anisotropic non-maximum suppression in industrial target detection [J]. Journal of Computer Applications, 2022, 42(7): 2210-2218.

Few‑shot target detection based on negative‑margin loss

基于负边距损失的小样本目标检测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 50

Related Articles 15

Recommended Articles

Metrics