Discrete Wavelet Transform-Based Capsule Network for Hyperspectral Image Classification

2025-01-08

AI Summary

To address the high computational cost and parameter redundancy of capsule networks in hyperspectral image classification, this paper proposes DWT-CapsNet. Methodologically, it introduces a novel discrete wavelet transform (DWT)-domain attention-based downsampling module to replace conventional convolutional downsampling; designs a multi-scale dynamic routing pruning mechanism to eliminate redundant capsule connections; and constructs a capsule pyramid fusion architecture integrated with locally connected self-attention for efficient joint spectral-spatial modeling. Experiments on mainstream benchmark datasets demonstrate that DWT-CapsNet achieves state-of-the-art classification accuracy while significantly reducing inference time (by 32.7%), FLOPs (by 41.5%), and model parameters (by 38.9%), thereby delivering both superior performance and practical efficiency.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

Hyperspectral image (HSI) classification is a crucial technique for remote sensing to build large-scale earth monitoring systems. HSI contains much more information than traditional visual images for identifying the categories of land covers. One recent feasible solution for HSI is to leverage CapsNets for capturing spectral-spatial information. However, these methods require high computational requirements due to the full connection architecture between stacked capsule layers. To solve this problem, a DWT-CapsNet is proposed to identify partial but important connections in CapsNet for a effective and efficient HSI classification. Specifically, we integrate a tailored attention mechanism into a Discrete Wavelet Transform (DWT)-based downsampling layer, alleviating the information loss problem of conventional downsampling operation in feature extractors. Moreover, we propose a novel multi-scale routing algorithm that prunes a large proportion of connections in CapsNet. A capsule pyramid fusion mechanism is designed to aggregate the spectral-spatial relationships in multiple levels of granularity, and then a self-attention mechanism is further conducted in a partially and locally connected architecture to emphasize the meaningful relationships. As shown in the experimental results, our method achieves state-of-the-art accuracy while keeping lower computational demand regarding running time, flops, and the number of parameters, rendering it an appealing choice for practical implementation in HSI classification.

Problem

• High Spectral Imaging
• Capsule Networks
• Computational Cost

Innovation

• DWT-CapsNet
• Attention Mechanism
• Efficient Classification