Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

TL;DR

This paper introduces APNT, a novel few-shot hyperspectral image classification method that combines prototype networks, transformers, and TransMix data augmentation to improve boundary pixel classification accuracy.

Contribution

It proposes augmenting prototype networks with TransMix and transformers to better handle boundary pixels and enhance diversity of training samples in hyperspectral image classification.

Findings

Achieves state-of-the-art performance on hyperspectral datasets.

Demonstrates improved robustness in boundary pixel classification.

Enhances training sample diversity with synthetic boundary patches.

Abstract

Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches centering around each pixel are often used for classification. However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify. These boundary patchs are mixed with multi-class spectral information. Inspired by this, we propose to augment the prototype network with TransMix for few-shot hyperspectrial image classification(APNT). While taking the prototype network as the backbone, it adopts the transformer as feature extractor to learn the pixel-to-pixel relation and pay different attentions to different pixels. At the same time, instead of directly using the patches which are cut from the hyperspectral images for training, it randomly mixs up two patches to imitate the boundary patches and uses the synthetic patches to train the model, with the aim to enlarge the number of hard training samples and enhance their diversity. And by following the data agumentation technique TransMix, the attention returned by the transformer is also used to mix up the labels of two patches to generate better labels for synthetic patches. Compared with existing methods, the proposed method has demonstrated sate of the art performance and better robustness for few-shot hyperspectral image classification in our experiments.