HyCoT: A Transformer-Based Autoencoder for Hyperspectral Image Compression
This work provides an incremental improvement in hyperspectral image compression for remote sensing applications by introducing a transformer-based method to enhance efficiency and performance.
The paper tackles hyperspectral image compression by proposing HyCoT, a transformer-based autoencoder that addresses limitations of existing convolutional models, achieving over 1 dB PSNR improvement across various compression ratios on the HySpecNet-11k dataset with reduced computational requirements.
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 .