HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis

2024/07/23 by Zhou, Fangqin, Mert Kilickaya, Joaquin Vanschoren +3 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.2407.16269

openalex publication_date 2024/07/23 · openalex created_date 2025/01/05 · openalex updated_date 2026/07/28

Abstract

Hyperspectral Imaging (HSI) plays an increasingly critical role in precise vision tasks within remote sensing, capturing a wide spectrum of visual data. Transformer architectures have significantly enhanced HSI task performance, while advancements in Transformer Architecture Search (TAS) have improved model discovery. To harness these advancements for HSI classification, we make the following contributions: i) We propose HyTAS, the first benchmark on transformer architecture search for Hyperspectral imaging, ii) We comprehensively evaluate 12 different methods to identify the optimal transformer over 5 different datasets, iii) We perform an extensive factor analysis on the Hyperspectral transformer search performance, greatly motivating future research in this direction. All benchmark materials are available at HyTAS.

Cited by

• L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers

Related

• Transformers Meet Hyperspectral Imaging: A Comprehensive Study of Models, Challenges and Open Problems
• Investigation of Hierarchical Spectral Vision Transformer Architecture for Classification of Hyperspectral Imagery
• EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification
• Transformers in Remote Sensing: A Survey
• Hyper-Restormer: A General Hyperspectral Image Restoration Transformer for Remote Sensing Imaging