[1]王 奇,靳华中,李文萱,等. 多尺度通道注意力机制的小样本图像分类算法[J].湖北工业大学学报,2022,(1):34-39+70.
　WANG Qi,JIN Huazhong,LI Wenxuan,et al. Few-Shot Image Classification Algorithm Based on Multi-scale Channel Attention[J].,2022,(1):34-39+70.
点击复制

 多尺度通道注意力机制的小样本图像分类算法()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2022年第1期
页码:
34-39+70
栏目:
湖北工业大学学报
出版日期:
2022-02-28

文章信息/Info

Title:
 Few-Shot Image Classification Algorithm Based on Multi-scale Channel Attention
文章编号:
1003-4684(2022)01-0034-06
作者:
 王 奇;  靳华中;  李文萱;  李晴晴
 湖北工业大学计算机学院， 湖北 武汉 430068
Author(s):
 WANG Qi;  JIN Huazhong;  LI Wenxuan;  LI Qingqing
 School of Computer Science, Hubei Univ. of Tech., Wuhan 430068, China
关键词:
 ; 小样本学习;  元学习;  关系网络;  注意力机制
Keywords:
 ; few-shot learning;  meta-Learning;  relation network;  attention
分类号:
TP311
文献标志码:
A
摘要:
 为了提升关系网络图像分类的准确度，在网络中引入多尺度通道注意力机制，提出了一种新的小样本图像分类算法。由于多尺度通道注意力机制能够关注样本特征空间的重要信息，该方法能够提取图像更丰富的多尺度特征，并通过关系度量，改善了分类结果。实验结果表明，在MiniImageNet和Omniglot数据集上，该算法对图像分类精度有明显的提高。
Abstract:
 In order to improve the accuracy of image classification, a multi-scale channel attention is introduced into Relation Network, and a new few-shot image classification algorithm is proposed. Since the multi-scale channel attention can focus on important information in the sample feature space, this method can extract richer multi-scale features of the image, and improve the classification results through relationship measurement. Experimental results show that the proposed algorithm can improve the accuracy of image classification on Mini Image Net and Omniglot data sets.

参考文献/References:

[1] KRIZHEVSKY A,SUTSKEVER I,HINTON G.Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25(2):1097-1105.
[2] RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2014:1-42.
[3] WANG Y, YAO Q, KWOK J, et al. Generalizing from a few examples: a survey on few-shot learning [EB/OL]. [2019-04-10]. arXiv:1904.05046, https:∥arxiv.org/abs/1904.05046.
[4] 耿瑞莹, 李永彬, 黎槟华. 小样本学习综述[EB/OL]. [2020-12-15]. https：∥zhuanlan.zhihu.com/p/61215293.
[5] 李新叶,龙慎鹏,朱婧.基于深度神经网络的少样本学习综述[J].计算机应用研究,2020,37(8):2241-2247.
[6] 赵凯琳,靳小龙,王元卓.小样本学习研究综述[J].软件学报,2020,32(2):1-16.
[7] 祝钧桃,姚光乐,张葛祥,等.深度神经网络的小样本学习综述[J].计算机工程与应用,2021,57(07):22-33.
[8] LU J, GONG P, YE J, et al. Learning from very few samples: a survey[J/OL]. [2020-09-06]. arXiv:2009.02653, https:∥arxiv.org/abs/2009.02653.
[9] 刘颖,雷研博,范九伦,等.基于小样本学习的图像分类技术综述[J].自动化学报,2021,47(2):297-315.
[10] PAN S J, QIANG Y. A Survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[11] HUISMAN M, RIJN J, PLAAT A. A survey of deep meta-learning [J/OL]. [2020-10-07]. arXiv:2010.03522. https:∥arxiv.org/abs/2010.03522.
[12] PAN W, LI B, CHONG Y. Image block compression based on dual-learning dictionaries[C]∥ 2020 12th International Conference on Advanced Computational Intelligence (ICACI). Dali: IEEE, 2020, 79-85.
[13] ZHU J, CHEN J, HU W, et al. Big learning with bayesian methods[J]. National Science Review, 2017(4):627-651.
[14] YANG, LIU, JIN R. Distance metric learning: a comprehensive survey. michigan state universiy[J], 2006: 1-51.
[15] ZAGORUYKO S, KOMODAKIS N. Learning to compare image patches via convolutional neural networks[C]∥ 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015, 4353-4361. 
[16] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[J/OL]. [2016-06-13]. arXiv:1606.04080, https:∥arxiv.org/abs/1606.04080.
[17] JAKE S, KEVIN S, RICHARD Z. Prototypical networks for few-shot learning[C]∥ Conference on Neural Information Processing Systems. Long Beach: NeurIPS, 2017,4077-4087.
[18] SUNG F, YANG Y, ZHANG L, 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: IEEE, 2018,1199-1208.
[19] 张碧陶,庞振全.融合强化学习和关系网络的样本分类[J].计算机工程与应用,2019,55(21):189-196+253.
[20] 金璐,刘士建,王霄,等.基于改进关系网络的小样本红外空中目标分类方法[J].光学学报,2020,40(8):87-96.
[21] 王年, 孟树林, 吴洛天, 等. 基于改进关系网络的小样本学习[J]. 安徽大学学报(自然科学版), 2020, 44(4):38-44.
[22] 张宸嘉,朱磊,俞璐.卷积神经网络中的注意力机制综述[J/OL].计算机工程与应用:1-10[2021-09-24].http:∥kns.cnki.net/kcms/detail/11.2127.tp.20210726.0839.002.html.
[23] JIE H, LI S, GANG S, et al. Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017:99.
[24] WANG Q, WU B, Zhu P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA,2020,11 531-11 539.
[25] LI X, WANG W, HU X, et al. Selective kernel networks[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, 510-519.
[26] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas,NV, USA, 2016,770-778.
[27] 付国栋,黄进,杨涛,等.改进CBAM的轻量级注意力模型[J/OL]. 计算机工程与应用: 1-8 [2021-05-10]. http:∥kns.cnki.net/kcms/detail/11.2127.TP.20210420.0924.006.html.
[28] LAKE B, SALAKHUTDINOV R, GROSS J, et al. Humanlevel concept learning through probabilistic program induction[J]. Science, 2015,350(6266):1332-1338.
[29] ZHANG HU, ZU KEKE, LU JIAN, et al. EPSANet: An efficient pyramid split attention block on convolutional neural network[J/OL]. [2021-05-30]. arXiv:2105.14447. https:∥arxiv.org/abs/2105.14447.
[30] FINN C, ABBEEL P, LEVINE S, et al. Model-agnostic meta-learning for fast adaptation of deep network[C]∥ International Conference on Machine Learning. Sydney: ICML, 2017, 1126-1135.

相似文献/References:

[1]熊韧,曹海印,王焱清,等.非牛顿润滑静压轴承的节流器流量方程修正[J].湖北工业大学学报,2019,34(5):6.
　XIONG Ren,CAO Haiyin,WANG Yanqing,et al.Modified restrictor flow equations of hydrostatic bearings ubricated by non-Newtonian fluids[J].,2019,34(1):6.
[2]王照远,曹 民,王 毅,等. 场景与数据双驱动的隧道图像拼接方法[J].湖北工业大学学报,2020,(4):11.
　WANG Zhaoyuan,CAO Min,WANG Yi,et al. Tunnel Image Stitching Method based on Scene and Data[J].,2020,(1):11.
[3]潘 健,梁佳成,陈凤娇,等. 单电流闭环多重PR控制的LCL型逆变器[J].湖北工业大学学报,2020,(4):16.
　PAN Jian,LIANG Jiacheng,CHEN Fengjiao,et al. Design of LCL Grid Connected Inverter based on Single Closed Loop Control and Multiple PR Controllers[J].,2020,(1):16.
[4]王晓光,赵 萌,文益雪,等. 定子闭口槽结构对永磁电机齿槽转矩影响分析[J].湖北工业大学学报,2020,(4):25.
　WANG Xiaoguang,ZHAO Meng,WEN Yixue,et al. Study on Cogging Torque and Vibration Noise of Permanent Magnet Motor with Segmental Stator and Closed-Slot[J].,2020,(1):25.
[5]宇 卫,凃玲英,陈 健. 风电场集中接入对集电线电流保护的影响[J].湖北工业大学学报,2020,(4):29.
　YU Wei,TU Lingying,CHEN Jian. Effect of the Collective Line Current Protection when Wind Farms are Centralized Accessed to the Power System[J].,2020,(1):29.
[6]廖政斌,王泽飞,祝 珊. 二惯量系统谐振在线抑制及相位补偿[J].湖北工业大学学报,2020,(4):34.
　LIAO Zhengbin,WANG Zefei,ZHU Shan. Online Resonance Suppression and Phase Compensation for Double Inertia System[J].,2020,(1):34.
[7]王 欣,游 颖,姜天翔,等. 面向3D打印过程的产品工艺设计和优化[J].湖北工业大学学报,2020,(4):39.
　WANG Xin,YOU Ying,JIANG Tianxiang,et al. Product Process Design and Optimization for 3D Printing Processes[J].,2020,(1):39.
[8]冉晶晶,文 红,罗雅梅,等. 全自动样品前处理平台及其控制系统[J].湖北工业大学学报,2020,(4):43.
　RAN Jingjing,WEN Hong,LUO Yamei,et al. Research on Automatic Sample Preprocessing Platform and its Control System[J].,2020,(1):43.
[9]杨 磊,马志艳,石 敏,等. 基于模糊PID的小型冷库过热度控制方法[J].湖北工业大学学报,2020,(4):43.
　YANG Lei,MA Zhiyan,SHI Min,et al. Research on Superheat Control Method of Small Cold Storage based on Fuzzy PID[J].,2020,(1):43.
[10]黄 晶,周细枝,周业望. 动态注塑成型模具的设计与实验研究[J].湖北工业大学学报,2020,(4):52.
　HUANG Jing,ZHOU Xizhi,ZHOU Yewang. Design and Experimental Study of Dynamic Injection Molding[J].,2020,(1):52.

备注/Memo

备注/Memo:
［收稿日期］ 2021-08-02
［基金项目］ 大学生创新创业训练计划项目（S201910500074）
［第一作者］ 王 奇（1997-），女，山西侯马人，湖北工业大学硕士研究生，研究方向为计算机视觉
［通信作者］ 靳华中（1973-），男，湖北洪湖人，湖北工业大学副教授，研究方向为计算机视觉
更新日期/Last Update: 2022-02-25