| 104 | 1 | 94 |
| 下载次数 | 被引频次 | 阅读次数 |
针对零样本图像分类中属性和特征之间映射不全面以及属性空间结构挖掘不充分问题，提出了基于关系有向图正则化的属性三因子分解模型。首先，利用属性矩阵三因子分解实现了属性空间和特征空间的映射；其次，通过权值矩阵构建了属性关系有向图；最后，在属性空间或特征空间计算测试样本和各测试类别的相似性，进而实现图像分类。在aPY和SUN数据集上的实验结果表明，所提模型有效地提高了零样本图像分类精度。
Abstract：Aiming at the problems of incomplete mapping between attributes and features, as well as the insufficient mining of the attribute space structure in zero-shot image classification, an attribute tri-factorization model with regularization of relation digraph was proposed. Firstly, the mapping between attribute space and feature space was achieved by matrix tri-factorization of attributes. Secondly, the attribute relation digraph was constructed using the weight matrix. Finally, the similarity between the testing sample and each testing class was calculated in either the attribute space or the feature space to finish image classification. Experimental results on aPY and SUN datasets showed that the proposed model was capable of efficiently improving the accuracy of zero-shot image classification.
[1] XIE G S,ZHANG Z,XIONG H,et al.Towards zero-shot learning:a brief review and an attention-based embedding network[J].IEEE transactions on circuits and systems for video technology,2023,33(3):1181-1197.
[2] 吴兰，李崇阳.深度加权子域自适应网络[J].郑州大学学报(理学版),2022,54(1):54-61.WU L,LI C Y.Deep-weight subdomain adaptive network [J].Journal of Zhengzhou university (natural science edition),2022,54(1):54-61.
[3] 彭涛，郑传锟，张自力，等.基于时空特征融合的语音情感识别[J].郑州大学学报(理学版),2022,54(4):42-48.PENG T,ZHENG C K,ZHANG Z L,et al.Speech emotion recognition based on spatio-temporal feature fusion [J].Journal of Zhengzhou university (natural science edition),2022,54(4):42-48.
[4] LAMPERT C H,NICKISCH H,HARMELING S.Attribute-based classification for zero-shot visual object categorization[J].IEEE transactions on pattern analysis and machine intelligence,2014,36(3):453-465.
[5] AKATA Z,REED S,WALTER D,et al.Evaluation of output embeddings for fine-grained image classification[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2015:2927-2936.
[6] YU Y L,JI Z,GUO J C,et al.Zero-shot learning via latent space encoding[J].IEEE transactions on cybernetics,2019,49(10):3755-3766.
[7] CHANGPINYO S,CHAO W L,GONG B Q,et al.Synthesized classifiers for zero-shot learning[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:5327-5336.
[8] VERMA V K,RAI P.A simple exponential family framework for zero-shot learning[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Cham:Springer International Publishing,2017:792-808.
[9] XU X,SHEN F M,YANG Y,et al.Matrix tri-factorization with manifold regularizations for zero-shot learning[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2017:2007-2016.
[10] DING C,LI T,PENG W,et al.Orthogonal nonnegative matrix t-factorizations for clustering[C]//Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2006:126-135.
[11] BOYD S P,VANDENBERGHE L.Convex optimization[M].New York:Cambridge University Press,2004.
[12] JAYARAMAN D,GRAUMAN K.Zero-shot recognition with unreliable attributes [C]//27th International Conference on Neural Information Processing Systems.Cambridge:MIT Press,2014:3464-3472.
[13] MAATEN L.Accelerating t-SNE using tree-based algorithms[J].Journal of machine learning research,2014,15(1):3221-3245.
[14] ROMERA-PAREDES B,TORR P H S.An embarrassingly simple approach to zero-shot learning[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning.New York:ACM Press,2015:2152-2161.
[15] ZHANG Z M,SALIGRAMA V.Zero-shot learning via semantic similarity embedding[C]//IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2016:4166-4174.
[16] ZHANG Z M,SALIGRAMA V.Zero-shot learning via joint latent similarity embedding[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE Press,2016:6034-6042.
[17] LONG Y,LIU L,SHEN F M,et al.Zero-shot learning using synthesised unseen visual data with diffusion regularisation[J].IEEE transactions on pattern analysis and machine intelligence,2018,40(10):2498-2512.
[18] YU Y L,JI Z,LI X,et al.Transductive zero-shot learning with a self-training dictionary approach[J].IEEE transactions on cybernetics,2018,48(10):2908-2919.
基本信息:
DOI：10.13705/j.issn.1671-6841.2023147
中图分类号:TP391.41
引用信息:
[1]张嘉睿,李瑞林,孔毅,等.基于关系有向图正则化的属性三因子分解模型[J].郑州大学学报(理学版),2025,57(01):67-73.DOI:10.13705/j.issn.1671-6841.2023147.
基金信息:
国家自然科学基金项目(42372329); 江苏省高等学校基础科学(自然科学)研究项目(21KJB520005); 江苏省自然科学基金项目(BK20200632); 徐州市基础研究计划(KC23019); 江苏师范大学科研项目(21XSRS001)
2023-06-14
2023
2025-01-14
2025
2024-04-19
2
2024-04-29
2024-04-29
2024-04-29