Pyramid Hierarchical Transformer for Hyperspectral Image Classification

TL;DR

This paper introduces PyFormer, a pyramid hierarchical transformer that improves hyperspectral image classification by efficiently capturing multi-level features and enhancing scalability for variable-length sequences.

Contribution

The paper proposes a novel pyramid-based hierarchical transformer architecture specifically designed for hyperspectral image classification, addressing efficiency and scalability issues of traditional transformers.

Findings

Outperforms traditional methods in accuracy and efficiency

Enhances robustness with disjoint sample integration

Effectively captures local and global context

Abstract

The traditional Transformer model encounters challenges with variable-length input sequences, particularly in Hyperspectral Image Classification (HSIC), leading to efficiency and scalability concerns. To overcome this, we propose a pyramid-based hierarchical transformer (PyFormer). This innovative approach organizes input data hierarchically into segments, each representing distinct abstraction levels, thereby enhancing processing efficiency for lengthy sequences. At each level, a dedicated transformer module is applied, effectively capturing both local and global context. Spatial and spectral information flow within the hierarchy facilitates communication and abstraction propagation. Integration of outputs from different levels culminates in the final input representation. Experimental results underscore the superiority of the proposed method over traditional approaches. Additionally, the incorporation of disjoint samples augments robustness and reliability, thereby highlighting the potential of our approach in advancing HSIC. The source code is available at https://github.com/mahmad00/PyFormer.