Document Type
Article
Publication Date
2-20-2026
Department
Department of Applied Computing
Abstract
Highlights: This work investigates the effect of spatial patch size on the classification accuracy and adversarial robustness of Vision Transformer-based architectures for hyperspectral image analysis. What are the main findings? Smaller patch sizes generally exhibit stronger adversarial robustness while maintaining comparable clean classification performance. Larger patch sizes tend to reduce robustness by increasing sensitivity to localized adversarial perturbations, with some dataset-dependent variations. What are the implications of the main findings? Spatial patch size is an important design consideration when applying Vision Transformers to hyperspectral image classification tasks. The findings provide practical guidance for informed patch-size selection in robust, deployment-aware transformer-based hyperspectral image classification models. Vision Transformers (ViTs) have demonstrated strong performance in hyperspectral image (HSI) classification; however, their robustness is highly sensitive to patch size. This study investigates the impact of spatial patch size on clean accuracy and adversarial robustness using a standard ViT and a Channel Attention Fusion variant (ViT-CAF). Patch sizes from 1 × 1 to 19 × 19 are evaluated across four benchmark datasets under FGSM, BIM, CW, PGD, and RFGSM attacks. Descriptive results show that smaller patches, particularly 1 × 1 and 3 × 3, generally yield higher adversarial accuracy, while larger patches amplify localized perturbations and degrade robustness. Parameter analysis indicates that patch-size-dependent variations arise mainly from the embedding layer, with the Transformer backbone remaining fixed, confirming that robustness differences are driven primarily by spatial context rather than model capacity. These findings reveal a trade-off between spatial granularity and adversarial resilience and provide guidance for patch size selection in ViT-based HSI applications.
Publication Title
Remote Sensing
Recommended Citation
Chandrappa, S.,
Paheding, S.,
&
Reyes-Angulo, A. A.
(2026).
Unraveling Patch Size Effects in Vision Transformers: Adversarial Robustness in Hyperspectral Image Classification.
Remote Sensing,
18(4).
http://doi.org/10.3390/rs18040656
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p2/2389
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Version
Publisher's PDF
Publisher's Statement
Copyright: © 2026 by the authors. Licensee MDPI, Basel, Switzerland. Publisher’s version of record: https://doi.org/10.3390/rs18040656