基于样本对元学习的小样本图像分类方法

doi:10.12263/DZXB.20210453

摘要/Abstract

摘要：

本文针对小样本图像分类问题，提出一种基于样本对的元学习（Pairwise-based Meta Learning，PML）方法.利用传递迁移学习对预训练好的Resnet50模型进行微调，得到一个更适应小样本任务的特征编码器，将该特征编码器作为元学习模型的初始特征编码器来训练模型，进一步增强了元学习模型的泛化能力；同时，本文还基于支持集与查询集样本之间的相似性提出元损失函数（Meta Loss，ML），其考虑了特征空间中查询集所有样本的相互关系，以此来缩小正样本类内距离，增加正负样本类间距离，从而提高分类精度.实验结果表明，本文的方法在1-shot、5-shot任务上分别达到了77.65%、89.65%的分类精度，较最新的元学习方法Meta-baseline分别提高7.38%、5.65%.

长摘要
全监督学习的高精度预测严重依赖于海量的标签样本，由于在许多领域样本难以获取，全监督模型的泛化能力往往不足。为了解决这一问题，本文针对小样本图像分类问题，提出一种基于样本对的元学习（Pairwise-based Meta Learning，PML）方法，该方法利用迁移学习和元学习的特点，实现了对小样本数据集的高精度分类，且提升了模型的泛化能力. 首先，为了解决源域与目标域差异过大的问题，利用传递迁移学习将先验知识传递式迁移到不同领域的特点，对预训练好的Resnet50模型进行微调，得到一个更适应小样本任务的特征编码器，将该特征编码器作为元学习模型的初始特征编码器来训练模型，进一步增强了元学习模型的泛化能力；同时，本文还基于支持集与查询集样本之间的多相似性提出元损失函数（Meta Loss，ML），利用正相对相似性P粗略挖掘困难样本对，再结合自相似性 S和负相对相似性N，进一步对样本对加权，其考虑了特征空间中查询集所有样本的相互关系，以此来缩小正样本类内距离，增加正负样本类间距离，从而提高了模型的分类精度. 实验结果表明，本文的方法在钢材显微组织图像数据集的1-shot、5-shot任务上分别达到了77.65%、89.65%的分类精度，较最新的元学习方法Meta-baseline分别提高7.38%、5.65%.

关键词: 小样本图像, 传递迁移学习, 元学习, 元损失函数

Abstract:

In this paper, a pairwise-based meta learning(PML) method is proposed for few-shot image classification. Transitive transfer learning is used to fine tune the pre-trained Resnet50 model to get a feature encoder that is more suitable for few shot task. The feature encoder is used as the initial feature encoder of the meta-learning model to train the model, which further enhances the generalization ability of the meta-learning model. Based on the similarity between the support set and the query set samples, a meta loss(ML) function is proposed, which considers the relationship between all the samples of the query set in the feature space, so as to reduce the within-class distance of positive samples and increase the between-class distance of positive and negative samples, thus improving the classification accuracy.The experimental results show that the classification accuracy of the methods in this paper is 77.65% and 89.65% on 1-shot and 5-shot tasks, respectively, and it is 7.38% and 5.65% higher than the latest meta-learning method, Meta-baseline.

Extended Abstract
Fully supervised learning models have achieved high precision prediction of many datasets, but it rely heavily on a large number of labeled samples. In many fields, it is difficult to obtain enough labeled samples, so the generalization ability of the fully supervised models is insufficient. In order to solve this problem, this paper proposes a pairwise-based meta learning (PML) method for few-shot image classification. Inspired by the characteristics of transfer learning and meta learning, the PML achieves high-precision classification of the few-shot datasets, and improves the generalization ability of the model. Firstly, the characteristics of transfer learning is transferring the prior knowledge to different fields, in order to reduce the difference of the source domain and target domain, the pre-trained Resnet50 model is fine-tuned to obtain a feature encoder that is more suitable for the few-shot tasks by transfer learning. The feature encoder is utilized as the initial feature encoder of the meta learning model to train the model, further enhancing the generalization ability of the meta learning model; at the same time, this paper also proposes a meta loss function (ML) based on the multiple similarities between the support set and the query set samples, it uses the positive relative similarity P to roughly mine teh difficult pairwise samples, and then combines the self similarity S and negative relative similarity N to further weight the pairwise samples, which takes into account the relationship of all samples in the query set in the feature space, so as to reduce the intra class distance of the positive samples and increase the inter class distance of the positive and negative samples, thus the classification accuracy of the model is improved. The experimental results show that the proposed method achieve 77.65% and 89.65% classification accuracy respectively on 1-shot and 5-shot tasks of steel microstructure image data set, which are 7.38% and 5.65% higher than the latest meta learning method meta baseline.

Key words: few-shot image, transitive transfer learning, meta learning, meta loss function

中图分类号:

TP391.4

李维刚, 甘平, 谢璐, 等. 基于样本对元学习的小样本图像分类方法[J]. 电子学报, 2022, 50(2): 295-304.

Wei-gang LI, Ping GAN, Lu XIE, et al. A Few-Shot Image Classification Method by Pairwise-Based Meta Learning[J]. Acta Electronica Sinica, 2022, 50(2): 295-304.

图/表 20

图1 PML方法示意图

图2 传递迁移学习训练范式

图3 初始网络

图4 5-way 1-shot元学习范式

表1 三种相似性在图像检索任务上的性能表现（数据来源于文献[16])

Recall	S/%	N/%	P/%	SN1/%	SN2/%	SP/%	NP/%	SNP/%
1	71.9	69.7	67.0	70.4	73.2	74.6	72.2	77.3
2	80.0	79.3	77.4	79.5	81.5	83.8	81.7	85.3
4	86.4	86.2	84.7	86.2	87.6	89.7	88.0	90.5
8	91.0	91.0	90.0	91.1	92.6	94.1	92.4	94.2

图5 三种样本对相似性示意图

图6 对挖掘和对加权示意图

图7 样本对权重示意图

表2 不同挖掘方法下样本平均精度（%）的置信区间及单个训练任务耗时的对比

Task	Weighting	Mining	Class $B$	Class $N$	Time/Train task	Weight File Size
1-shot 1 024维	Our method	Our method	98.85 $±$ 0.14	75.87 $±$ 0.97	0.176 s	33 581KB
1-shot 1 024维	Our method	MS mining method	98.57 $±$ 0.16	75.09 $±$ 0.98	0.256 s	33 581KB
1-shot 2 048维	Our method	Our method	99.14 $±$ 0.12	76.81 $±$ 0.96	0.192 s	92 145KB
1-shot 2 048维	Our method	MS mining method	98.79 $±$ 0.14	76.16 $±$ 0.96	0.256 s	92 145KB
5-shot 1 024维	Our method	Our method	99.50 $±$ 0.09	89.63 $±$ 0.69	0.224 s	33 581KB
5-shot 1 024维	Our method	MS mining method	99.44 $±$ 0.10	89.45 $±$ 0.70	0.288 s	33 581KB
5-shot	Our method	Our method	99.76 $±$ 0.06	88.40 $±$ 0.73	0.224 s	92 145KB
2 048维	Our method	MS mining method	99.64 $±$ 0.08	88.00 $±$ 0.74	0.288 s	92 145KB

表2 不同挖掘方法下样本平均精度（%）的置信区间及单个训练任务耗时的对比

Task	Weighting	Mining	Class $B$	Class $N$	Time/Train task	Weight File Size
1-shot 1 024维	Our method	Our method	98.85 $±$ 0.14	75.87 $±$ 0.97	0.176 s	33 581KB
1-shot 1 024维	Our method	MS mining method	98.57 $±$ 0.16	75.09 $±$ 0.98	0.256 s	33 581KB
1-shot 2 048维	Our method	Our method	99.14 $±$ 0.12	76.81 $±$ 0.96	0.192 s	92 145KB
1-shot 2 048维	Our method	MS mining method	98.79 $±$ 0.14	76.16 $±$ 0.96	0.256 s	92 145KB
5-shot 1 024维	Our method	Our method	99.50 $±$ 0.09	89.63 $±$ 0.69	0.224 s	33 581KB
5-shot 1 024维	Our method	MS mining method	99.44 $±$ 0.10	89.45 $±$ 0.70	0.288 s	33 581KB
5-shot	Our method	Our method	99.76 $±$ 0.06	88.40 $±$ 0.73	0.224 s	92 145KB
2 048维	Our method	MS mining method	99.64 $±$ 0.08	88.00 $±$ 0.74	0.288 s	92 145KB

表3 不同损失函数在新类N上样本平均精度（%）的置信区间对比

Index	Loss	Setup	1-shot/1 024维	1-shot/2 048维	5-shot/1 024维	5-shot/2 048维
①	Cross entropy Loss		75.85 $±$ 0.97	75.99 $±$ 0.97	89.56 $±$ 0.69	87.17 $±$ 0.76
②	MS weighting+ MS mining	$λ$ =0.5	74.97 $±$ 0.98	75.97 $±$ 0.97	89.43 $±$ 0.70	87.93 $±$ 0.74
③	MS weighting+Our mining	$λ$ =0.5	75.51 $±$ 0.97	76.69 $±$ 0.96	89.60 $±$ 0.69	88.21 $±$ 0.73
④	ML- $μ$ Loss	$η =$ 0.9， $λ$ =0.5	75.60 $±$ 0.97	76.72 $±$ 0.96	89.61 $±$ 0.69	88.32 $±$ 0.73
⑤	ML- $η$ Loss	$μ$ =0.75， $λ$ =0.5	75.59 $±$ 0.97	76.75 $±$ 0.96	89.61 $±$ 0.69	88.23 $±$ 0.73
⑥	ML（our）	$μ$ =0.75， $η =$ 0.9， $λ$ =0.5	75.87 $±$ 0.97	76.81 $±$ 0.96	89.63 $±$ 0.69	88.40 $±$ 0.72

表3 不同损失函数在新类N上样本平均精度（%）的置信区间对比

Index	Loss	Setup	1-shot/1 024维	1-shot/2 048维	5-shot/1 024维	5-shot/2 048维
①	Cross entropy Loss		75.85 $±$ 0.97	75.99 $±$ 0.97	89.56 $±$ 0.69	87.17 $±$ 0.76
②	MS weighting+ MS mining	$λ$ =0.5	74.97 $±$ 0.98	75.97 $±$ 0.97	89.43 $±$ 0.70	87.93 $±$ 0.74
③	MS weighting+Our mining	$λ$ =0.5	75.51 $±$ 0.97	76.69 $±$ 0.96	89.60 $±$ 0.69	88.21 $±$ 0.73
④	ML- $μ$ Loss	$η =$ 0.9， $λ$ =0.5	75.60 $±$ 0.97	76.72 $±$ 0.96	89.61 $±$ 0.69	88.32 $±$ 0.73
⑤	ML- $η$ Loss	$μ$ =0.75， $λ$ =0.5	75.59 $±$ 0.97	76.75 $±$ 0.96	89.61 $±$ 0.69	88.23 $±$ 0.73
⑥	ML（our）	$μ$ =0.75， $η =$ 0.9， $λ$ =0.5	75.87 $±$ 0.97	76.81 $±$ 0.96	89.63 $±$ 0.69	88.40 $±$ 0.72

表4 不同模型下2类样本平均精度（%）的置信区间

Model	Transfer model		PML
Task	1-shot	5-shot	1-shot	5-shot
Class $N$	88.57 $±$ 1.14	95.17 $±$ 0.77	92.27 $±$ 0.96	96.97 $±$ 0.61

表4 不同模型下2类样本平均精度（%）的置信区间

Model	Transfer model		PML
Task	1-shot	5-shot	1-shot	5-shot
Class $N$	88.57 $±$ 1.14	95.17 $±$ 0.77	92.27 $±$ 0.96	96.97 $±$ 0.61

图8 钢材显微组织示意图

图9 Kylberg Texture数据集??部分类别示意图

图10 不同模型在新类样本上的平均精度（%）

图11 新类数据集N上不同超参数ε取值下的分类精度

图12 mini-ImageNet数据集上不同超参数ε取值下的分类精度

图13 tiered-ImageNet数据集上不同超参数ε取值下的分类精度

表5 不同元学习对比(在新类上样本平均精度（%）的置信区间)

Model	1-shot	5-shot
Matching Networks^［1］	47.11 $±$ 1.13	59.71 $±$ 1.11
MAML^［20］	49.27 $±$ 1.13	67.28 $±$ 1.06
Prototypical Networks^［6］	51.63 $±$ 1.13	66.16 $±$ 1.07
Relation Networks^［21］	54.70 $±$ 1.13	71.51 $±$ 1.02
Meta-Baseline^［9］	70.27 $±$ 1.03	84.00 $±$ 0.83
Pre-training model（ours）	63.53 $±$ 1.09	82.43 $±$ 0.86
Transfer model（ours）	72.41 $±$ 1.01	83.98 $±$ 0.83
PML（ours）	77.65 $±$ 0.94	89.65 $±$ 0.69

表5 不同元学习对比(在新类上样本平均精度（%）的置信区间)

Model	1-shot	5-shot
Matching Networks^［1］	47.11 $±$ 1.13	59.71 $±$ 1.11
MAML^［20］	49.27 $±$ 1.13	67.28 $±$ 1.06
Prototypical Networks^［6］	51.63 $±$ 1.13	66.16 $±$ 1.07
Relation Networks^［21］	54.70 $±$ 1.13	71.51 $±$ 1.02
Meta-Baseline^［9］	70.27 $±$ 1.03	84.00 $±$ 0.83
Pre-training model（ours）	63.53 $±$ 1.09	82.43 $±$ 0.86
Transfer model（ours）	72.41 $±$ 1.01	83.98 $±$ 0.83
PML（ours）	77.65 $±$ 0.94	89.65 $±$ 0.69

表6 不同元学习方法在mini-ImageNet数据集上样本平均精度（%）的置信区间(#指应用DropBlock[22]和标签平滑.结果参考文献[9,23,24])

Model	Backone	1-shot	5-shot	Model	Backone	1-shot	5-shot
Matching Networks^［1］	ConvNet-4	43.56 $±$ 0.84	55.31 $±$ 0.73	Prototypical Networks^［6］	ConvNet-4	48.70 $±$ 1.84	63.11 $±$ 0.92
Activation to Parameter^［25］	WRN-28-10	59.60 $±$ 0.41	73.74 $±$ 0.19	LEO^［26］	WRN-28-10	61.76 $±$ 0.08	77.59 $±$ 0.12
Chen，et al^［27］	ResNet-18	51.87 $±$ 0.77	75.68 $±$ 0.63	SNAIL^［28］	ResNet-12	55.71 $±$ 0.99	68.88 $±$ 0.92
AdaResNet^［29］	ResNet-12	56.88 $±$ 0.62	71.94 $±$ 0.57	TADAM^［30］	ResNet-12	58.50 $±$ 0.30	76.70 $±$ 0.30
MTL^［8］	ResNet-12	61.20 $±$ 1.80	75.50 $±$ 0.80	MetaOptNet ^#^［13］	ResNet-12	62.64 $±$ 0.61	78.63 $±$ 0.46
MetaOptNet^［13］	ResNet-12	60.33 $±$ 0.61	76.61 $±$ 0.46	Meta-Baseline^［9］	ResNet-12	63.17 $±$ 0.23	79.26 $±$ 0.17
E³BM^［23］	ResNet-12	63.80 $± 0.4$ 0	80.10 $±$ 0.30	PSST^［24］	ResNet-12	64.05 $±$ 0.49	80.24 $±$ 0.49
Meta-Baseline+ML（our）	ResNet-12	64.10 $±$ 0.22	80.48 $±$ 0.16

表6 不同元学习方法在mini-ImageNet数据集上样本平均精度（%）的置信区间(#指应用DropBlock[22]和标签平滑.结果参考文献[9,23,24])

Model	Backone	1-shot	5-shot	Model	Backone	1-shot	5-shot
Matching Networks^［1］	ConvNet-4	43.56 $±$ 0.84	55.31 $±$ 0.73	Prototypical Networks^［6］	ConvNet-4	48.70 $±$ 1.84	63.11 $±$ 0.92
Activation to Parameter^［25］	WRN-28-10	59.60 $±$ 0.41	73.74 $±$ 0.19	LEO^［26］	WRN-28-10	61.76 $±$ 0.08	77.59 $±$ 0.12
Chen，et al^［27］	ResNet-18	51.87 $±$ 0.77	75.68 $±$ 0.63	SNAIL^［28］	ResNet-12	55.71 $±$ 0.99	68.88 $±$ 0.92
AdaResNet^［29］	ResNet-12	56.88 $±$ 0.62	71.94 $±$ 0.57	TADAM^［30］	ResNet-12	58.50 $±$ 0.30	76.70 $±$ 0.30
MTL^［8］	ResNet-12	61.20 $±$ 1.80	75.50 $±$ 0.80	MetaOptNet ^#^［13］	ResNet-12	62.64 $±$ 0.61	78.63 $±$ 0.46
MetaOptNet^［13］	ResNet-12	60.33 $±$ 0.61	76.61 $±$ 0.46	Meta-Baseline^［9］	ResNet-12	63.17 $±$ 0.23	79.26 $±$ 0.17
E³BM^［23］	ResNet-12	63.80 $± 0.4$ 0	80.10 $±$ 0.30	PSST^［24］	ResNet-12	64.05 $±$ 0.49	80.24 $±$ 0.49
Meta-Baseline+ML（our）	ResNet-12	64.10 $±$ 0.22	80.48 $±$ 0.16

表7 不同元学习方法在tiered-ImageNet数据集上样本平均精度（%）的置信区间(参考文献[9,13]的结果)

Model	Backone	1-shot	5-shot	Model	Backone	1-shot	5-shot
MAML^［20］	ConvNet-4	51.67 $±$ 1.81	70.30 $±$ 1.75	Prototypical Networks^［6］	ConvNet-4	53.31 $±$ 0.89	72.69 $±$ 0.74
Relation Networks^［21］	ConvNet-4	54.48 $±$ 0.93	71.32 $±$ 0.78	LEO^［26］	WRN-28-10	66.33 $±$ 0.05	81.44 $±$ 0.09
MetaOptNet^［13］	ResNet-12	65.99 $±$ 0.72	81.56 $±$ 0.53	Meta-Baseline^［9］	ResNet-12	68.62 $±$ 0.27	83.29 $±$ 0.18
Meta-Baseline+ML（our）	ResNet-12	68.09 $±$ 0.28	83.97 $±$ 0.18

表7 不同元学习方法在tiered-ImageNet数据集上样本平均精度（%）的置信区间(参考文献[9,13]的结果)

Model	Backone	1-shot	5-shot	Model	Backone	1-shot	5-shot
MAML^［20］	ConvNet-4	51.67 $±$ 1.81	70.30 $±$ 1.75	Prototypical Networks^［6］	ConvNet-4	53.31 $±$ 0.89	72.69 $±$ 0.74
Relation Networks^［21］	ConvNet-4	54.48 $±$ 0.93	71.32 $±$ 0.78	LEO^［26］	WRN-28-10	66.33 $±$ 0.05	81.44 $±$ 0.09
MetaOptNet^［13］	ResNet-12	65.99 $±$ 0.72	81.56 $±$ 0.53	Meta-Baseline^［9］	ResNet-12	68.62 $±$ 0.27	83.29 $±$ 0.18
Meta-Baseline+ML（our）	ResNet-12	68.09 $±$ 0.28	83.97 $±$ 0.18

参考文献 30

1	VINYALSO, BLUNDELLC, LILLICRAPT, et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain: MIT Press, 2016: 3630-3638.
2	季鼎承, 蒋亦樟, 王士同. 基于域与样例平衡的多源迁移学习方法[J]. 电子学报, 2019, 47(3): 692-699.
	JIDing-cheng, JIANGYi-zhang, WANGShi-tong. Multi-source transfer learning method by balancing both the domains and instances[J]. Acta Electronica Sinica, 2019, 47(3): 692-699. (in Chinese)
3	PANS J, YANGQ. A survey on transfer learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010, 22(10): 1345-1359.
4	李凡长, 刘洋, 吴鹏翔, 等. 元学习研究综述[J]. 计算机学报, 2021, 44(2): 422-446.
	LIFan-chang, LIUYang, WUPeng-xiang, et al. A surveyon recent advancesin meta-learning[J]. Chinese Journal of Computers, 2021, 44(2): 422-446. (in Chinese)
5	LAKEB, SALAKHUTDINOVR, GROSSJ, et al. One shot learning of simple visual concepts[C]//Proceedings of the Annual Meeting of the Cognitive Science Society. California: eScholarship, 2011: 33(33).
6	SNELLJ, SWERSKYK, ZEMELR. Prototypical networks for few-shot learning[C]//Proceedings of the International Conference on Neural Information Processing Systems. Massachusetts, USA: MIT Press, 2017: 4077-4087.
7	TANB, SONGY, ZHONGE, et al. Transitive transfer learning[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA: ACM, 2015: 1155-1164.
8	SUNQ, LIUY, CHUAT S, et al. Meta-transfer learning for few-shot learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 403-412.
9	CHENY, WANGX, LIUZ, et al. A new meta-baseline for few-shot learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE, 2020: 04390.
10	LUBBERSN, LOOKMANT, BARROSK. Inferring low-dimensional microstructure representations using convolutional neural networks[J]. Physical Review E, 2017, 96(5): 052111.
11	DECOSTB L, FRANCIST, HOLME A. Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructures[J]. Acta Materialia, 2017, 133: 30-40.
12	AZIMIS M, BRITZD, ENGSTLERM, et al. Advanced steel microstructural classification by deep learning methods[J]. Scientific Reports, 2018, 8(1): 2128.
13	LEEK, MAJIS, RAVICHANDRANA, SOATTOS. Meta-learning with differentiable convex optimization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 10657-10665.
14	RENM, TRIANTAFILLOUE, RAVIS, et al. Meta-learning for semi-supervised few-shot classification[C]//Proceedings of the International Conference on Learning Representations. https://openreview.net, 2018: 1803.00676.
15	HEK, ZHANGX, RENS, et al. Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.
16	WANGX, HANX, HUANGW, et al. Multi-similarity loss with general pair weighting for deep metric learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 5022-5030.
17	WEINBERGERK Q, SAULL K. Distance metric learning for large margin nearest neighbor classification[J]. Journal of Machine Learning Research, 2009, 10(2): 207-244.
18	LOSHCHILOVI, HUTTERF. Decoupled weight decay regularization[C]//Proceedings of the European International Conference on Learning Representations(ICLR). https://openreview.net, 2017: 1711.05101.
19	ZEILERMD, TAYLORG W, FERGUSR. Adaptive deconvolutional networks for mid and high level feature learning[C]//Proceedings of the International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2018-2025.
20	FINNC, ABBEELP, LEVINES. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the International Conference on Machine Learning. New York, USA: ACM, 2017: 1126-1135.
21	SUNGF, YANGY, ZHANGL, et al. Learning to compare: Relation network for few-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 1199-1208.
22	GHIASIG, LINTY, LEQ V. Dropblock: A regularization method for convolutional networks[C]//Proceedings of the Advances in Neural Information Processing Systems(NIPS). Massachusetts, USA: MIT Press, 2018: 10727-10737.
23	LIUY, SCHIELEB, SUNQ. An ensemble of epoch-wise empirical Bayes for few-shot learning[C]//Proceedings of the European Conference on Computer Vision. Berlin: Springer, Cham, 2020: 404-421.
24	CHENZ, GEJ, ZHANH, et al. Pareto self-supervised training for few-shot learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA: IEEE, 2021: 13663-13672.
25	QIAOS, LIUC, SHENW, et al. Few-shot image recognition by predicting parameters from activations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 7229-7238.
26	RUSUA A, RAOD, SYGNOWSKIJ, et al. Meta-learning with latent embedding optimization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 1807. 05960.
27	CHENWY, LIUYC, KIRAZ, et al. A closer look at few-shot classification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 1904. 04232.
28	MISHRAN, ROHANINEJADM, et al. A simple neural attentive meta-learner[C]//Proceedings of the 6th International Conference on Learning Representations. https://openreview.net, 2018: 1707.03141.
29	MUNKHDALAIT, YUANX, MEHRIS, et al. Rapid adaptation with conditionally shifted neurons[C]//Proceedings of the International Conference on Machine Learning. Stockholm, Sweden: PMLR, 2018: 3664-3673.
30	ORESHKINB, L'OPEZP R, LACOSTEA. Tadam: Task dependent adaptive metric for improved few-shot learning[C]//Proceedings of the Advances in Neural Information Processing Systems. USA Massachusetts: MIT Press, 2018: 721-731.

[1]	彭锦佳, 王辉兵. 基于异构卷积神经网络集成的无监督行人重识别方法[J]. 电子学报, 2023, (): 1-13.
[2]	郭凯红, 崔明茜, 刘婷婷. 模糊知识测度下图像脉冲噪声去除方法[J]. 电子学报, 2023, (): 1-14.
[3]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[4]	张晶, 王翌歆, 任永功. 统一全局空间表达的脑电信号跨被试情感识别[J]. 电子学报, 2023, (): 1-9.
[5]	但志平, 方帅领, 孙航, 李晶, 万俊. 基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾[J]. 电子学报, 2023, (): 1-14.
[6]	张智, 易华挥, 郑锦. 聚焦小目标的航拍图像目标检测算法[J]. 电子学报, 2023, (): 1-12.
[7]	姚睿, 朱享彬, 周勇, 王鹏, 张艳宁, 赵佳琦. 基于重要特征的视觉目标跟踪可迁移黑盒攻击方法[J]. 电子学报, 2023, (): 1-9.
[8]	孙锐, 张磊, 余益衡, 张旭东. 基于局部异构聚合图卷积网络的跨模态行人重识别[J]. 电子学报, 2023, (): 1-16.
[9]	张杰, 廖盛斌, 张浩峰, 陈得宝. 基于类别扩展的广义零样本图像分类方法[J]. 电子学报, 2023, (): 1-13.
[10]	吴晓雨, 蒲禹江, 王生进, 刘子豪. 基于语义嵌入学习的特类视频识别[J]. 电子学报, 2023, (): 1-13.
[11]	苏天康, 宋慧慧, 樊佳庆, 张开华. 深度信号引导学习混合变换器的高性能无监督视频目标分割[J]. 电子学报, 2023, (): 1-8.
[12]	林彬, 王华通, 封全喜. 基于双模型竞争机制的目标跟踪算法[J]. 电子学报, 2023, (): 1-7.
[13]	王子为, 鲁继文, 周杰. 基于自适应梯度优化的二值神经网络[J]. 电子学报, 2023, 51(2): 257-266.
[14]	唐利明, 熊点华, 方壮. 基于比尔朗伯定律的变分水平集模型[J]. 电子学报, 2023, 51(2): 416-426.
[15]	杨利平, 侯振威, 辜小花, 郝峻永. 弱标签声音事件检测的空间-通道特征表征与自注意池化[J]. 电子学报, 2023, 51(2): 297-306.