mlsanityData to 7 Oct 2026

HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis

arXiv 2407.16269 ↗First posted 23 Jul 2024cs.CVcited by 3

Not on the map. Why?

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 23 Jul 2024.

Builds on

25 of 42 references.

References · 25

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  4. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  5. 2017Progressive Neural Architecture Searchcited by 483
  6. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
  7. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 467
  8. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
  9. 2020Neural Architecture Search without Trainingcited by 241
  10. 2021Zero-Cost Proxies for Lightweight NAScited by 194
  11. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  12. 2021SpectralFormer: Rethinking Hyperspectral Image Classification with Transformerscited by 168
13 more
  1. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  2. 2019Deep Learning for Hyperspectral Image Classification: An Overviewcited by 121
  3. 2018Faster gaze prediction with dense networks and Fisher pruningcited by 92
  4. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 57
  5. 2021GLiT: Neural Architecture Search for Global and Local Image Transformercited by 53
  6. 2022Training-free Transformer Architecture Searchcited by 33
  7. 2019BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budgetcited by 26
  8. 2021EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Searchcited by 24
  9. 2023Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunitiescited by 21
  10. 2022FreeREA: Training-Free Evolution-based Architecture Searchcited by 10
  11. 2021Zero-Cost Operation Scoring in Differentiable Architecture Searchcited by 9
  12. 2023Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbationscited by 6
  13. 2023Locality-Aware Hyperspectral Classificationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformerscited by 5
  2. 2025AI-Driven HSI: Multimodality, Fusion, Challenges, and the Deep Learning Revolutioncited by 1
  3. 2026Hyperspectral Image Models: Technical Reportcited by 0