《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (10): 3200-3208.DOI: 10.11772/j.issn.1001-9081.2023101416
收稿日期:
2023-10-19
修回日期:
2023-12-21
接受日期:
2023-12-22
发布日期:
2024-10-15
出版日期:
2024-10-10
通讯作者:
谢莉
作者简介:
谢莉(1985—),女,重庆人,副教授,博士,主要研究方向:图像处理、软测量建模、系统辨识 xieli@jiangnan.edu.cn基金资助:
Li XIE1(), Weiping SHU1, Junjie GENG1, Qiong WANG2, Hailin YANG3
Received:
2023-10-19
Revised:
2023-12-21
Accepted:
2023-12-22
Online:
2024-10-15
Published:
2024-10-10
Contact:
Li XIE
About author:
SHU Weiping, born in 1998, M. S. candidate. His research interests include deep learning, image processing.Supported by:
摘要:
基于深度学习的图像分类算法通常依赖大量训练数据,然而对于医学领域中的宫颈细胞分类任务,难以实现收集大量的图像数据。为了在少量图像样本的条件下正确分类宫颈细胞,提出一种结合加权原型和自适应张量子空间的小样本分类算法(CWP-ATS)。首先,结合预训练技术和元学习,保证特征提取网络从元训练集中学习更多的先验知识;其次,在原型计算过程中采用最大均值差异算法为每个支持集样本赋予合适的权重,并采用转导学习算法修正,以获得更准确的原型;最后,利用多线性主成分分析算法将每类样本投影至各自的低维张量子空间,从而在不破坏原始张量特征自然结构的前提下,在低维空间中学习高效的自适应子空间分类器。在小样本Herlev宫颈细胞图像的2-way 10-shot和3-way 10-shot分类任务中,与DeepBDC(Deep Brownian Distance Covariance)算法相比,CWP-ATS的分类准确度分别提高了2.43和3.23个百分点;当元测试集中30%的样本受噪声干扰时,与原型网络相比,CWP-ATS的分类准确度有超过20个百分点的提升。实验结果表明,CWP-ATS有效提高了对小样本宫颈细胞的分类准确度和鲁棒性。
中图分类号:
谢莉, 舒卫平, 耿俊杰, 王琼, 杨海麟. 结合加权原型和自适应张量子空间的小样本宫颈细胞分类[J]. 计算机应用, 2024, 44(10): 3200-3208.
Li XIE, Weiping SHU, Junjie GENG, Qiong WANG, Hailin YANG. Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace[J]. Journal of Computer Applications, 2024, 44(10): 3200-3208.
数据属性 | 类别 | 图像数 |
---|---|---|
元训练集 | 轻度非典型增生 | 182 |
中度非典型增生 | 146 | |
重度非典型增生 | 197 | |
原位癌 | 150 | |
元测试集 | 浅表鳞状上皮 | 74 |
中层鳞状上皮 | 70 | |
柱状上皮 | 98 |
表1 Herlev宫颈细胞图像数据集分布
Tab. 1 Distribution of Herlev cervical cell image dataset
数据属性 | 类别 | 图像数 |
---|---|---|
元训练集 | 轻度非典型增生 | 182 |
中度非典型增生 | 146 | |
重度非典型增生 | 197 | |
原位癌 | 150 | |
元测试集 | 浅表鳞状上皮 | 74 |
中层鳞状上皮 | 70 | |
柱状上皮 | 98 |
特征提取网络 | 参数量/106 | 分类准确度/% | |||||
---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | ||
Conv_64F | 0.113 | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
ResNet-7 | 1.219 | 93.94±0.90 | 94.88±0.79 | 95.75±0.54 | 86.26±0.73 | 89.24±0.55 | 90.68±0.48 |
ResNet-12 | 8.008 | 89.13±1.20 | 90.65±1.17 | 91.16±1.04 | 78.23±0.84 | 80.59±0.75 | 82.67±0.61 |
表2 不同特征提取网络对应的分类结果
Tab. 2 Classification results corresponding to different feature extraction networks
特征提取网络 | 参数量/106 | 分类准确度/% | |||||
---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | ||
Conv_64F | 0.113 | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
ResNet-7 | 1.219 | 93.94±0.90 | 94.88±0.79 | 95.75±0.54 | 86.26±0.73 | 89.24±0.55 | 90.68±0.48 |
ResNet-12 | 8.008 | 89.13±1.20 | 90.65±1.17 | 91.16±1.04 | 78.23±0.84 | 80.59±0.75 | 82.67±0.61 |
算法 | 分类准确度 | |||||
---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | |
ProtoNet[ | 87.10±0.94 | 90.06±0.72 | 92.25±0.65 | 78.62±0.65 | 81.54±0.60 | 87.08±0.49 |
DSN[ | 89.27±0.88 | 91.34±0.77 | 93.26±0.79 | 79.92±0.77 | 83.44±0.58 | 87.31±0.47 |
RelationNet[ | 85.22±1.04 | 88.20±0.65 | 89.69±0.56 | 68.76±0.74 | 73.35±0.58 | 77.34±0.49 |
RegressionNet[ | 89.68±0.96 | 91.15±0.83 | 93.16±0.71 | 79.53±0.82 | 83.65±0.64 | 87.72±0.46 |
MML[ | 90.46±0.76 | 92.01±0.62 | 93.52±0.53 | 80.99±0.52 | 84.02±0.41 | 87.98±0.33 |
TDE-FSL[ | 88.16±0.88 | 91.21±0.67 | 92.88±0.61 | 80.11±0.61 | 83.26±0.55 | 88.16±0.46 |
DeepBDC[ | 90.61±0.92 | 92.35±0.69 | 93.67±0.56 | 80.81±0.69 | 84.25±0.61 | 88.35±0.55 |
APP2S[ | 90.16±0.71 | 91.91±0.65 | 93.01±0.49 | 80.92±0.54 | 84.36±0.43 | 88.42±0.37 |
本文算法 | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
表3 本文算法与经典算法的对比结果 (%)
Tab. 3 Comparison results between proposed algorithm and classical algorithms
算法 | 分类准确度 | |||||
---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | |
ProtoNet[ | 87.10±0.94 | 90.06±0.72 | 92.25±0.65 | 78.62±0.65 | 81.54±0.60 | 87.08±0.49 |
DSN[ | 89.27±0.88 | 91.34±0.77 | 93.26±0.79 | 79.92±0.77 | 83.44±0.58 | 87.31±0.47 |
RelationNet[ | 85.22±1.04 | 88.20±0.65 | 89.69±0.56 | 68.76±0.74 | 73.35±0.58 | 77.34±0.49 |
RegressionNet[ | 89.68±0.96 | 91.15±0.83 | 93.16±0.71 | 79.53±0.82 | 83.65±0.64 | 87.72±0.46 |
MML[ | 90.46±0.76 | 92.01±0.62 | 93.52±0.53 | 80.99±0.52 | 84.02±0.41 | 87.98±0.33 |
TDE-FSL[ | 88.16±0.88 | 91.21±0.67 | 92.88±0.61 | 80.11±0.61 | 83.26±0.55 | 88.16±0.46 |
DeepBDC[ | 90.61±0.92 | 92.35±0.69 | 93.67±0.56 | 80.81±0.69 | 84.25±0.61 | 88.35±0.55 |
APP2S[ | 90.16±0.71 | 91.91±0.65 | 93.01±0.49 | 80.92±0.54 | 84.36±0.43 | 88.42±0.37 |
本文算法 | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
算法 | 主干网络 | 分类准确度 | |||||
---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | ||
MetaMed[ | Conv_32F | 90.12 | 91.21 | 93.37 | 75.08 | 80.00 | 84.08 |
PFEMed[ | 双路WRN-28-10 | 94.21±0.81 | 95.05±0.71 | 95.46±0.58 | 87.62±0.67 | 90.03±0.51 | 92.11±0.44 |
本文算法 | Conv_64F | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
表4 与文献中小样本宫颈细胞分类算法的对比结果 (%)
Tab. 4 Comparison results with classification algorithms for few-shot cervical cells in literature
算法 | 主干网络 | 分类准确度 | |||||
---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | ||
MetaMed[ | Conv_32F | 90.12 | 91.21 | 93.37 | 75.08 | 80.00 | 84.08 |
PFEMed[ | 双路WRN-28-10 | 94.21±0.81 | 95.05±0.71 | 95.46±0.58 | 87.62±0.67 | 90.03±0.51 | 92.11±0.44 |
本文算法 | Conv_64F | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
模型 | 预训练 | 加权原型 | 张量子空间 | 原型修正 | 分类准确度 | |||||
---|---|---|---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | |||||
Ⅰ | 87.10±0.94 | 90.06±0.72 | 92.25±0.65 | 78.62±0.65 | 81.54±0.60 | 87.08±0.49 | ||||
Ⅱ | √ | 89.41±1.10 | 91.76±0.89 | 93.68±0.60 | 83.13±0.69 | 87.97±0.49 | 88.26±0.43 | |||
Ⅲ | √ | √ | 89.61±0.96 | 92.46±0.65 | 94.42±0.54 | 83.51±0.66 | 88.20±0.47 | 88.89±0.50 | ||
Ⅳ | √ | √ | √ | 91.99±0.84 | 94.46±0.68 | 95.63±0.50 | 85.26±0.62 | 88.90±0.46 | 91.21±0.39 | |
Ⅴ | √ | √ | √ | √ | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
表5 小样本Herlev数据集上的消融实验结果 (%)
Tab. 5 Results of ablation experiments on few-shot Herlev dataset
模型 | 预训练 | 加权原型 | 张量子空间 | 原型修正 | 分类准确度 | |||||
---|---|---|---|---|---|---|---|---|---|---|
2-way 3-shot | 2-way 5-shot | 2-way 10-shot | 3-way 3-shot | 3-way 5-shot | 3-way 10-shot | |||||
Ⅰ | 87.10±0.94 | 90.06±0.72 | 92.25±0.65 | 78.62±0.65 | 81.54±0.60 | 87.08±0.49 | ||||
Ⅱ | √ | 89.41±1.10 | 91.76±0.89 | 93.68±0.60 | 83.13±0.69 | 87.97±0.49 | 88.26±0.43 | |||
Ⅲ | √ | √ | 89.61±0.96 | 92.46±0.65 | 94.42±0.54 | 83.51±0.66 | 88.20±0.47 | 88.89±0.50 | ||
Ⅳ | √ | √ | √ | 91.99±0.84 | 94.46±0.68 | 95.63±0.50 | 85.26±0.62 | 88.90±0.46 | 91.21±0.39 | |
Ⅴ | √ | √ | √ | √ | 94.56±0.77 | 95.43±0.69 | 96.10±0.54 | 88.14±0.62 | 90.12±0.45 | 91.58±0.38 |
1 | 中国抗癌协会妇科肿瘤专业委员会. 宫颈癌诊断与治疗指南(第四版)[J]. 中国实用妇科与产科杂志, 2018, 34(6): 613-622. |
Gynecological Oncology Professional Committee of China Anti-Cancer Association. Guidelines for the diagnosis and treatment of cervical cancer (fourth edition) [J]. Chinese Journal of Practical Gynecology and Obstetrics, 2018, 34(6): 613-622. | |
2 | SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2017[J]. CA: A Cancer Journal for Clinicians, 2017, 67(1): 7-30. |
3 | 韩颖, 赵萌, 陈胜勇,等. 基于最大截面特征的病变宫颈细胞核的自动筛查[J]. 计算机应用, 2019, 39(4): 1189-1195. |
HAN Y, ZHAO M, CHEN S Y, et al. Automatic screening of abnormal cervical nucleus based on maximum section feature[J]. Journal of Computer Applications, 2019, 39(4): 1189-1195. | |
4 | WANG P, WANG L, LI Y, et al. Automatic cell nuclei segmentation and classification of cervical Pap smear images[J]. Biomedical Signal Processing and Control, 2019, 48: 93-103. |
5 | 赵越, 曾立波, 吴琼水. 卷积神经网络的宫颈细胞图像分类[J]. 计算机辅助设计与图形学学报, 2018, 30(11): 2049-2054. |
ZHAO Y, ZENG L B, WU Q S. Classification of cervical cells based on convolution neural network[J]. Journal of Computer-Aided Design & Computer Graphics, 2018, 30(11): 2049-2054. | |
6 | 杨洪刚, 陈洁洁, 徐梦飞. 双线性内卷神经网络用于眼底疾病图像分类[J]. 计算机应用, 2023, 43(1): 259-264. |
YANG H G, CHEN J J, XU M F. Bilinear involution neural network for image classification of fundus diseases[J]. Journal of Computer Applications, 2023, 43(1): 259-264. | |
7 | 周迪, 张自力, 陈佳,等. 基于EfficientNetV2和物体上下文表示的胃癌图像分割方法[J]. 计算机应用, 2023, 43(9): 2955-2962. |
ZHOU D, ZHANG Z L, CHEN J, et al. Stomach cancer image segmentation method based on EfficientNetV2 and object-contextual representation[J]. Journal of Computer Applications, 2023, 43(9): 2955-2962. | |
8 | 胡卉, 蔡金清. 基于深度卷积神经网络的宫颈细胞涂片的病变细胞分类[J]. 软件工程, 2018, 21(8): 19-22. |
HU H, CAI J Q. Lesion cell classification of cervical smear based on deep convolution neural network[J]. Software Engineering, 2018, 21(8): 19-22. | |
9 | SHI J, WANG R, ZHENG Y, et al. Cervical cell classification with graph convolutional network[J]. Computer Methods and Programs in Biomedicine, 2021, 198: 105807. |
10 | JIA A D, LI B Z, ZHANG C C. Detection of cervical cancer cells based on strong feature CNN-SVM network[J]. Neurocomputing, 2020, 411: 112-127. |
11 | 董阳, 潘海为, 崔倩娜,等. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054. |
DONG Y, PAN H W, CUI Q N, et al. Few-shot segmentation method for multi-modal magnetic resonance images of brain tumor[J]. Journal of Computer Applications, 2021, 41(4): 1049-1054. | |
12 | JIANG W, HUANG K, GENG J, et al. Multi-scale metric learning for few-shot learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(3): 1091-1102. |
13 | JIANG H, GAO M, LI H, et al. Multi-learner based deep meta-learning for few-shot medical image classification[J]. IEEE Journal of Biomedical and Health Informatics, 2023, 27(1): 17-28. |
14 | SINGH R, BHARTI V, PUROHIT V, et al. MetaMed: few-shot medical image classification using gradient-based meta-learning[J]. Pattern Recognition, 2021, 120: 108111. |
15 | DAI Z, YI J, YAN L, et al. PFEMed: few-shot medical image classification using prior guided feature enhancement[J]. Pattern Recognition, 2023, 134: 109108. |
16 | 安胜彪, 郭昱岐, 白宇,等. 小样本图像分类研究综述[J]. 计算机科学与探索, 2023, 17(3): 511-532. |
AN S B, GUO Y Q, BAI Y, et al. Survey of few-shot image classification research[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(3): 511-532. | |
17 | ZHANG R, CHE T, GHAHRAMANI Z, et al. MetaGAN: an adversarial approach to few-shot learning[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2018: 2371-2380. |
18 | FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks [C]// Proceedings of the 34th International Conference on Machine Learning. New York: JMLR.org, 2017: 1126-1135. |
19 | RUSU A A, RAO D, SYGNOWSKI J, et al. Meta-learning with latent embedding optimization [EB/OL]. [2023-12-16]. . |
20 | 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: Curran Associates, 2016: 3637-3645. |
21 | SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2017: 4080-4090. |
22 | ORESHKIN B, RODRÍGUEZ LÓPEZ P, LACOSTE A. TADAM: task dependent adaptive metric for improved few-shot learning[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2018: 719-729. |
23 | JI Z, CHAI X, YU Y, et al. Improved prototypical networks for few-shot learning[J]. Pattern Recognition Letters, 2020, 140: 81-87. |
24 | YANG L, LI L, ZHANG Z, et al. DPGN: distribution propagation graph network for few-shot learning[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 13387-13396. |
25 | HOU R, CHANG H, MA B, et al. Cross attention network for few-shot classification[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2019: 4003-4014. |
26 | SIMON C, KONIUSZ P, NOCK R, et al. Adaptive subspaces for few-shot learning[C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 4135-4144. |
27 | TIAN Y, WANG Y, KRISHNAN D, et al. Rethinking few-shot image classification: a good embedding is all you need? [C]// Proceedings of the 16th European Conference on Computer Vision. Cham: Springer, 2020: 266-282. |
28 | LAENEN S, BERTINETTO L. On episodes, prototypical networks, and few-shot learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 24581-24592. |
29 | GRETTON A, BORGWARDT K M, RASCH M J, et al. A kernel two-sample test[J]. The Journal of Machine Learning Research, 2012, 13: 723-773. |
30 | KIM B, KHANNA R, KOYEJO O. Examples are not enough, learn to criticize! Criticism for interpretability[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2016: 2288-2296. |
31 | LU H, PLATANIOTIS K N, VENETSANOPOULOS A N. MPCA: multilinear principal component analysis of tensor objects[J]. IEEE Transactions on Neural Networks, 2008, 19(1): 18-39. |
32 | JANTZEN J, NORUP J, DOUNIAS G, et al. Pap-smear benchmark data for pattern classification[C]// Proceedings of the 2015 Nature Inspired Smart Information System: EU Co-ordination Action. Albufeira, Portugal: NiSIS, 2005: 1-9. |
33 | 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. |
34 | DEVOS A, GROSSGLAUSER M. Regression networks for meta-learning few-shot classification [EB/OL]. [2023-12-16]. . |
35 | CHEN H, LI H, LI Y, et al. Multi-level metric learning for few-shot image recognition[C]// Proceedings of the 31st International Conference on Artificial Neural Networks. Cham: Springer, 2022: 243-254. |
36 | XING L, SHAO S, LIU W, et al. Learning task-specific discriminative embeddings for few-shot image classification[J]. Neurocomputing, 2022, 488: 1-13. |
37 | XIE J, LONG F, LV J, et al. Joint distribution matters: deep Brownian distance covariance for few-shot classification[C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 7962-7971. |
38 | MA R, FANG P, DRUMMOND T, et al. Adaptive poincaré point to set distance for few-shot classification[C]// Proceedings of the 2022 AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2022, 36(2): 1926-1934. |
[1] | 王东炜, 刘柏辰, 韩志, 王艳美, 唐延东. 基于低秩分解和向量量化的深度网络压缩方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 1987-1994. |
[2] | 翟飞宇, 马汉达. 基于DenseNet的经典-量子混合分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1905-1910. |
[3] | 余新言, 曾诚, 王乾, 何鹏, 丁晓玉. 基于知识增强和提示学习的小样本新闻主题分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1767-1774. |
[4] | 肖斌, 杨模, 汪敏, 秦光源, 李欢. 独立性视角下的相频融合领域泛化方法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1002-1009. |
[5] | 周雯, 谌雨章, 温志远, 王诗琦. 基于位置编码重叠切块嵌入和多尺度通道交互注意力的鱼类图像分类[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3209-3216. |
[6] | 陈彤, 位纪伟, 何仕远, 宋井宽, 杨阳. 基于自适应攻击强度的对抗训练方法[J]. 《计算机应用》唯一官方网站, 2024, 44(1): 94-100. |
[7] | 于碧辉, 蔡兴业, 魏靖烜. 基于提示学习的小样本文本分类方法[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2735-2740. |
[8] | 姜钧舰, 刘达维, 刘逸凡, 任酉贵, 赵志滨. 基于孪生网络的小样本目标检测算法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2325-2329. |
[9] | 王彬, 向甜, 吕艺东, 王晓帆. 基于NSGA‑Ⅱ的自适应多尺度特征通道分组优化算法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1401-1408. |
[10] | 李振亮, 李波. 基于矩阵分解的卷积神经网络改进方法[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 685-691. |
[11] | 文凯, 薛晓, 季娟. 面向复杂图像分类的共享转换矩阵胶囊网络[J]. 《计算机应用》唯一官方网站, 2023, 43(11): 3411-3417. |
[12] | 申志军, 穆丽娜, 高静, 史远航, 刘志强. 细粒度图像分类综述[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 51-60. |
[13] | 魏佳璇, 杜世康, 于志轩, 张瑞生. 图像分类中的白盒对抗攻击技术综述[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2732-2741. |
[14] | 任炜, 白鹤翔. 基于全局与局部标签关系的多标签图像分类方法[J]. 《计算机应用》唯一官方网站, 2022, 42(5): 1383-1390. |
[15] | 季长清, 高志勇, 秦静, 汪祖民. 基于卷积神经网络的图像分类算法综述[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1044-1049. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||