# HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis

arXiv: https://arxiv.org/abs/2407.16269 · HTML: https://mlsanity.com/paper/2407.16269/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Deep Learning for Hyperspectral Image Classification: An Overview](https://mlsanity.com/paper/1910.12861/) (2019)
- [Faster gaze prediction with dense networks and Fisher pruning](https://mlsanity.com/paper/1801.05787/) (2018)
- [ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients](https://mlsanity.com/paper/2301.11300/) (2023)
- [GLiT: Neural Architecture Search for Global and Local Image Transformer](https://mlsanity.com/paper/2107.02960/) (2021)
- [Training-free Transformer Architecture Search](https://mlsanity.com/paper/2203.12217/) (2022)
- [BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget](https://mlsanity.com/paper/1906.04113/) (2019)
- [EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search](https://mlsanity.com/paper/2102.08099/) (2021)
- [Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2307.01998/) (2023)
- [FreeREA: Training-Free Evolution-based Architecture Search](https://mlsanity.com/paper/2207.05135/) (2022)
- [Zero-Cost Operation Scoring in Differentiable Architecture Search](https://mlsanity.com/paper/2106.06799/) (2021)
- [Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations](https://mlsanity.com/paper/2306.05031/) (2023)
- [Locality-Aware Hyperspectral Classification](https://mlsanity.com/paper/2309.01561/) (2023)

## Built on by (most cited first, 3 of 3)

- [L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers](https://mlsanity.com/paper/2505.07300/) (2025)
- [AI-Driven HSI: Multimodality, Fusion, Challenges, and the Deep Learning Revolution](https://mlsanity.com/paper/2502.06894/) (2025)
- [Hyperspectral Image Models: Technical Report](https://mlsanity.com/paper/2609.39871/) (2026)

## Abstract (arXiv)

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.