Open AccessResearch on image classification method based on improved multi-scale relational network
Author(s) -
Wenfeng Zheng,
Xiangjun Liu,
Lirong Yin
Publication year - 2021
Publication title -
peerj. computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.806
H-Index - 24
ISSN - 2376-5992
DOI - 10.7717/peerj-cs.613
Subject(s) - meta learning (computer science) , computer science , artificial intelligence , machine learning , generalization , benchmark (surveying) , sample (material) , deep learning , object (grammar) , scale (ratio) , set (abstract data type) , process (computing) , data mining , mathematics , mathematical analysis , chemistry , physics , management , geodesy , chromatography , quantum mechanics , programming language , economics , task (project management) , geography , operating system
Small sample learning aims to learn information about object categories from a single or a few training samples. This learning style is crucial for deep learning methods based on large amounts of data. The deep learning method can solve small sample learning through the idea of meta-learning “how to learn by using previous experience.” Therefore, this paper takes image classification as the research object to study how meta-learning quickly learns from a small number of sample images. The main contents are as follows: After considering the distribution difference of data sets on the generalization performance of measurement learning and the advantages of optimizing the initial characterization method, this paper adds the model-independent meta-learning algorithm and designs a multi-scale meta-relational network. First, the idea of META-SGD is adopted, and the inner learning rate is taken as the learning vector and model parameter to learn together. Secondly, in the meta-training process, the model-independent meta-learning algorithm is used to find the optimal parameters of the model. The inner gradient iteration is canceled in the process of meta-validation and meta-test. The experimental results show that the multi-scale meta-relational network makes the learned measurement have stronger generalization ability, which further improves the classification accuracy on the benchmark set and avoids the need for fine-tuning of the model-independent meta-learning algorithm.