RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classification

TL;DR

RS-MetaNet introduces a meta-learning approach with a novel loss function to improve few-shot remote sensing scene classification, achieving state-of-the-art results on multiple datasets with limited labeled samples.

Contribution

The paper presents RS-MetaNet, a task-level meta-learning method with Balance Loss, enhancing generalization in few-shot remote sensing scene classification.

Findings

Achieves state-of-the-art accuracy on three remote sensing datasets.

Effectively classifies scenes with only 1-20 labeled samples.

Outperforms existing few-shot classification methods.

Abstract

Training a modern deep neural network on massive labeled samples is the main paradigm in solving the scene classification problem for remote sensing, but learning from only a few data points remains a challenge. Existing methods for few-shot remote sensing scene classification are performed in a sample-level manner, resulting in easy overfitting of learned features to individual samples and inadequate generalization of learned category segmentation surfaces. To solve this problem, learning should be organized at the task level rather than the sample level. Learning on tasks sampled from a task family can help tune learning algorithms to perform well on new tasks sampled in that family. Therefore, we propose a simple but effective method, called RS-MetaNet, to resolve the issues related to few-shot remote sensing scene classification in the real world. On the one hand, RS-MetaNet raises the level of learning from the sample to the task by organizing training in a meta way, and it learns to learn a metric space that can well classify remote sensing scenes from a series of tasks. We also propose a new loss function, called Balance Loss, which maximizes the generalization ability of the model to new samples by maximizing the distance between different categories, providing the scenes in different categories with better linear segmentation planes while ensuring model fit. The experimental results on three open and challenging remote sensing datasets, UCMerced\_LandUse, NWPU-RESISC45, and Aerial Image Data, demonstrate that our proposed RS-MetaNet method achieves state-of-the-art results in cases where there are only 1-20 labeled samples.