高光谱成像
增采样
小波
人工智能
计算机科学
模式识别(心理学)
联营
小波变换
信息丢失
计算机视觉
图像(数学)
作者
Muhammad Ahmad,Usman Ghous,Muhammad Usama,Manuel Mazzara
出处
期刊:IEEE Geoscience and Remote Sensing Letters
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:: 1-1
被引量:1
标识
DOI:10.1109/lgrs.2024.3353909
摘要
Transformers have proven effective for Hyperspectral Image Classification (HSIC) but often incorporate average pooling that results in information loss. This paper presents WaveFormer, a novel transformer-based approach that leverages wavelet transforms for invertible downsampling. This preserves data integrity while enabling attention learning. Specifically, WaveFormer unifies downsampling with wavelet transforms to decompress feature maps without loss. This provides an efficient tradeoff between performance and computation. Furthermore, the wavelet decomposition enhances the interaction between structural and shape information in image patches and channel maps. To evaluate WaveFormer, we conducted extensive experiments on two benchmark hyperspectral datasets. Our results demonstrate that WaveFormer achieves state-of-the-art classification accuracy, obtaining overall accuracies of 95.66% and 96.54% on the Pavia University and the University of Houston datasets, respectively. By integrating wavelet transforms, WaveFormer presents a new transformer architecture for hyperspectral imagery that achieves superior classification without information loss from average pooling.
科研通智能强力驱动
Strongly Powered by AbleSci AI