Abstract
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.
Highlights
Deep learning has made significant progress in computer vision fields, but only on the premise that they have a large amount of annotated data (Ni et al, 2019; Vinyals et al, 2016; Zheng, Liu & Yin, 2021)
Considering that the small sample image classification method based on metric learning can be adapted to the new task without fine-tuning, the multi-scale meta-relational network adopts the model-agnostic meta-learning algorithm (MAML) algorithm to learn and find the optimal parameters of the model in the meta-training process, and eliminates the inner gradient iteration in the meta-validation and meta-testing process
According to Finn, Abbeel & Levine (2017) in the experiment of MAML and MetaSGD, a convolutional neural network composed of four layers of convolution and one layer of full connection is adopted as a learning device
Summary
Deep learning has made significant progress in computer vision fields, but only on the premise that they have a large amount of annotated data (Ni et al, 2019; Vinyals et al, 2016; Zheng, Liu & Yin, 2021). It is impractical to acquire large amounts of data in real life. As far as deep learning is concerned, fitting into a more complex model requires more data to have good generalization ability. Once there is a lack of data, deep learning technology can make the in-sample training effect good, but the generalization performance of new samples is poor. Inspired by the human ability to learn quickly from a small sample, many researchers have become increasingly aware of the need to study machine learning from a small sample.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
