HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression

TL;DR

HyCoT introduces a transformer-based autoencoder for hyperspectral image compression, outperforming existing models in quality and efficiency by capturing global dependencies and reducing training costs.

Contribution

The paper presents HyCoT, a novel transformer-based autoencoder for hyperspectral image compression, with a simple training set reduction method to accelerate training.

Findings

HyCoT surpasses state-of-the-art in PSNR by over 1 dB.

HyCoT achieves lower computational complexity.

Effective training set reduction accelerates model training.

Abstract

The development of learning-based hyperspectral image (HSI) compression models has recently attracted significant interest. Existing models predominantly utilize convolutional filters, which capture only local dependencies. Furthermore,they often incur high training costs and exhibit substantial computational complexity. To address these limitations, in this paper we propose Hyperspectral Compression Transformer (HyCoT) that is a transformer-based autoencoder for pixelwise HSI compression. Additionally, we apply a simple yet effective training set reduction approach to accelerate the training process. Experimental results on the HySpecNet-11k dataset demonstrate that HyCoT surpasses the state of the art across various compression ratios by over 1 dB of PSNR with significantly reduced computational requirements. Our code and pre-trained weights are publicly available at https://git.tu-berlin.de/rsim/hycot .