FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pretraining

TL;DR

FactoFormer introduces a factorized hyperspectral transformer with self-supervised pretraining, effectively capturing spectral and spatial information, leading to state-of-the-art classification performance on multiple datasets.

Contribution

The paper proposes a novel factorized spectral-spatial transformer with self-supervised pretraining for hyperspectral images, addressing limitations of previous models and enhancing performance.

Findings

Achieves state-of-the-art results on six hyperspectral datasets.

Effectively captures spectral and spatial interactions in HSI data.

Demonstrates the benefits of factorized and self-supervised pretraining strategies.

Abstract

Hyperspectral images (HSIs) contain rich spectral and spatial information. Motivated by the success of transformers in the field of natural language processing and computer vision where they have shown the ability to learn long range dependencies within input data, recent research has focused on using transformers for HSIs. However, current state-of-the-art hyperspectral transformers only tokenize the input HSI sample along the spectral dimension, resulting in the under-utilization of spatial information. Moreover, transformers are known to be data-hungry and their performance relies heavily on large-scale pretraining, which is challenging due to limited annotated hyperspectral data. Therefore, the full potential of HSI transformers has not been fully realized. To overcome these limitations, we propose a novel factorized spectral-spatial transformer that incorporates factorized self-supervised pretraining procedures, leading to significant improvements in performance. The factorization of the inputs allows the spectral and spatial transformers to better capture the interactions within the hyperspectral data cubes. Inspired by masked image modeling pretraining, we also devise efficient masking strategies for pretraining each of the spectral and spatial transformers. We conduct experiments on six publicly available datasets for HSI classification task and demonstrate that our model achieves state-of-the-art performance in all the datasets. The code for our model will be made available at https://github.com/csiro-robotics/factoformer.