Research on image classification method based on improved multi-scale relational network

doi:10.7717/peerj-cs.613

Return

Research on image classification method based on improved multi-scale relational network

2021-07-21

143

Wenfeng Zheng

Xiangjun Liu *

Lirong Yin

DOI：10.7717/peerj-cs.613

Original

Save

View PDF

Abstract

En 中文

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.

Keywords:

Less sample learning

Meta-learning

Multi-scale characteristics

Model-independent

Image classification

META-SGD

Multi-scale relational network

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.