[1]郎文溪,孙 涵.基于视觉一致性增强的细粒度图像检索[J].计算机技术与发展,2022,32(12):12-20.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 003]
　LANG Wen-xi,SUN Han.Fine-grained Image Retrieval Based on Strengthened Visual Consistency[J].,2022,32(12):12-20.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 003]
点击复制

基于视觉一致性增强的细粒度图像检索()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年12期
页码:
12-20
栏目:
综述
出版日期:
2022-12-10

文章信息/Info

Title:
Fine-grained Image Retrieval Based on Strengthened Visual Consistency
文章编号:
1673-629X(2022)12-0012-09
作者:
郎文溪; 孙 涵
南京航空航天大学 计算机科学与技术学院,江苏 南京 211106
Author(s):
LANG Wen-xi; SUN Han
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
细粒度图像检索; 弱监督; 对比学习; 哈希; 视觉一致性
Keywords:
fine-grained image retrieval; weak supervision; contrast learning; hashing; visual consistency
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 12. 003
摘要:
细粒度图像检索旨在从大类图像中检索出特定子类的图像。 得益于卷积神经网络的快速发展,细粒度图像检索的精度和速度均取得突破,但其性能仍受限于不同子类图像间高相似性和同一子类图像间的高差异性。 针对上述问题,该文提出了一种基于对比学习和视觉一致性增强的细粒度图像检索框架 CVCS-Net。 CVCS-Net 由判别性特征挖掘模块、视觉一致性增强模块和语义哈希编码模块组成,在挖掘类间图像判别性特征的同时,通过增强类内图像的视觉一致性来提升模型对类内图像差异的容忍度。 判别性特征挖掘模块学习空间注意力图来定位图像的判别性区域并获得这些区域对应的局部特征表示;视觉一致性增强模块提升模型对类内图像差异的鲁棒性;而语义哈希编码模块基于量化损失和位平衡损失进一步学习紧凑的哈希码用于检索。 CVCS-Net 在 CUB200-2011、Stanford Dogs 和 Stanford Cars 的 mAP 分别可达到 0. 859 1、0. 856 4 和 0. 918 3,相较于当前其他检索方法能够取得更好的检索结果。
Abstract:
Fine-grained image retrieval aims at retrieving images of specific sub-categories from general categories of images. Thanks tothe rapid development of convolutional neural networks,there has been a breakthrough in the accuracy and speed of fine-grained imageretrieval. However,its performance is still limited by the high similarity between images of different sub - categories and the highdifference between images of the same sub -category. Therefore,a contrast learning and strengthened visual consistency CVCS - Net isproposed. CVCS-Net consists of three key modules:discriminative feature mining,strengthened visual consistency and semantic hashcoding. The discriminative feature mining module learns spatial attention maps to locate discriminative regions of images and obtainslocal feature representations corresponding to these regions; the strengthened visual consistency module improves the robustness of themodel to intra-class image differences; and the semantic hash coding module further learns compact hash codes for retrieval based onquantization loss and bit balance loss. CVCS-Net can get mAPs of 0. 859 1,0. 856 4 and 0. 918 3 for CUB200-2011,Stanford Dogs andStanford Cars,respectively,which can get better results compared with other current retrieval methods.

相似文献/References:

[1]彭昀磊,牛 耘.基于弱监督的蛋白质交互识别[J].计算机技术与发展,2018,28(02):19.[doi:10．3969/j．issn．1673－629X．2018．02．005]
　PENG Yunlei,NIU Yun.Protein－protein Interaction Identification Based on Weak Supervision[J].,2018,28(12):19.[doi:10．3969/j．issn．1673－629X．2018．02．005]
[2]毛宇薇,牛耘.基于关键词的蛋白质交互关系识别[J].计算机技术与发展,2019,29(03):18.[doi:10.3969/ j. issn.1673-629X.2019.03.004]
　MAO Yu-wei,NIU Yun.Protein-protein Interaction Identification Based on Keywords[J].,2019,29(12):18.[doi:10.3969/ j. issn.1673-629X.2019.03.004]
[3]张振宇,朱培栋,赵东升.一种用于病案相似性度量的弱监督学习算法[J].计算机技术与发展,2019,29(09):1.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 001]
　ZHANG Zhen-yu,ZHU Pei-dong,ZHAO Dong-sheng.A Weakly Supervised Machine Learning Algorithm Applied to Similarity Measure of Medical Records[J].,2019,29(12):1.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 001]
[4]白瑜颖,刘宁钟,姜晓通.结合注意力混合裁剪的细粒度分类网络[J].计算机技术与发展,2021,31(10):38.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 007]
　BAI Yu-ying,LIU Ning-zhong,JIANG Xiao-tong.Fine Grained Image Classification Network Combined with Attention CutMix[J].,2021,31(12):38.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 007]
[5]范业嘉,孙 涵.基于轻量级深度哈希网络的细粒度图像检索[J].计算机技术与发展,2021,31(10):128.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 022]
　FAN Ye-jia,SUN Han.Fine-grained Image Retrieval Based on Lightweight Deep Hash Network[J].,2021,31(12):128.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 022]
[6]赵晓芹.融合局部特征与全局特征的场景文本检测算法[J].计算机技术与发展,2022,32(S2):25.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 004]
　ZHAO Xiao-qin.Scene Text Detection Algorithm Combining Local and Global Features[J].,2022,32(12):25.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 004]
[7]殷梓轩,孙 涵.基于注意力金字塔与监督哈希的细粒度图像检索[J].计算机技术与发展,2023,33(03):20.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 004]
　YIN Zi-xuan,SUN Han.Fine-grained Image Retrieval Based on Supervised Hashing with Attention Pyramid[J].,2023,33(12):20.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 004]

更新日期/Last Update: 2022-12-10