Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (3): 693-706.DOI: 10.3778/j.issn.1673-9418.2301070

• Graphics·Image • Previous Articles     Next Articles

Prototype Rectification Few-Shot Classification Model with Dual-Path Cooperation

LYU Jia, ZENG Mengyao, DONG Baosen   

  1. 1. College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China
    2. Chongqing Center of Engineering Technology Research on Digital Agriculture & Service, Chongqing 401331, China
  • Online:2024-03-01 Published:2024-03-01

双路径合作的原型矫正小样本分类模型

吕佳,曾梦瑶,董保森   

  1. 1. 重庆师范大学 计算机与信息科学学院,重庆 401331
    2. 重庆市数字农业服务工程技术研究中心,重庆 401331

Abstract: In the learning process of the metric-based meta-learning, there are some problems, such as the lack of prior knowledge acquired due to the distribution of scarce data, the interference of weakly related or unrelated features extracted from a single-view sample, and the deviations of representative features caused by classification. To solve these problems, a prototype rectification few-shot classification model with dual-path cooperation is proposed in this paper. Firstly, the dual-path cooperation module adaptively highlights key features and weakens weakly related features from a multi-view perspective, and makes full use of feature information to obtain prior knowledge to improve the expression ability of features. Secondly, the problem of intra-class prototype with deviations is solved by the prototype rectification classification strategy with the sample feature information of the query set. Finally, the model parameters are updated reversely by means of the loss function, and the classification accuracy of the model is improved. Comparative experiments of 5-way 1-shot and 5-way 5-shot are conducted on five public datasets. Compared with baseline model, on the miniImageNet dataset, the accuracy is increased by 5.57 percentage points and 3.90 percentage points. On the tieredImageNet dataset, the accuracy is increased by 5.68 percentage points and 3.93 percentage points. On the CUB dataset, the accuracy is increased by 6.93 percentage points and 3.13 percentage points. On the CIFAR-FS dataset, the accuracy is increased by 8.03 percentage points and 1.65 percentage points. On the FC-100 dataset, the accuracy is increased by 4.25 percentage points and 4.89 percentage points. Experimental results show that the proposed model has good performance in the field of few-shot learning, and the modules in the model can be migrated to other models.

Key words: few-shot learning, meta-learning, metric learning, adaptive dual-path cooperation learning, prototype rectification

摘要: 基于度量的元学习在学习过程中存在由于稀缺数据分布导致习得的先验知识不足、从样本中提取到的单一视图特征易受弱相关或无关特征的干扰以及因分类造成的代表性特征偏差的问题。针对这些问题,提出了一种双路径合作的原型矫正小样本分类模型。首先,通过双路径合作模块从多视图角度自适应地突出关键特征和弱化弱相关特征,充分利用特征信息获得先验知识来提升特征的表达能力;其次,通过基于查询集样本特征信息的原型矫正分类策略来解决类内原型的偏差问题;最后,通过损失函数反向更新模型参数,模型分类准确率得以提升。在五个公开的数据集上进行了5-way 1-shot和5-way 5-shot对比实验,较基准模型而言,在miniImageNet数据集上,准确率提升了5.57个百分点和3.90个百分点;在tieredImageNet数据集上,准确率提升了5.68个百分点和3.93个百分点;在CUB数据集上,准确率提升了6.93个百分点和3.13个百分点;在CIFAR-FS数据集上,准确率提升了8.03个百分点和1.65个百分点;在FC-100数据集上,准确率提升了4.25个百分点和4.89个百分点。实验结果表明,提出的双路径合作的原型矫正小样本分类模型能在小样本学习领域有良好的性能,且模型中的模块可迁移到其他模型中使用。

关键词: 小样本学习, 元学习, 度量学习, 自适应双路径合作学习, 原型矫正