HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis
This work addresses the need for efficient transformer design in hyperspectral imaging for remote sensing applications, though it is incremental as it benchmarks existing methods rather than proposing new ones.
The authors tackled the problem of optimizing transformer architectures for hyperspectral image classification by creating HyTAS, the first benchmark for transformer architecture search in this domain, evaluating 12 methods across 5 datasets to identify optimal models.
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.