Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 241

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Spectral–Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework

Zhong, Zilong, Li, Ying, Ma, Lingfei, Li, Jonathan, Zheng, Wei-Shi·2022·IEEE Transactions on Geoscience and Remote Sensing

Abstract

Neural networks have dominated the research of hyperspectral image classification, attributing to the feature learning capacity of convolution operations. However, the fixed geometric structure of convolution kernels hinders long-range interaction between features from distant locations. In this article, we propose a novel spectral–spatial transformer network (SSTN), which consists of spatial attention and spectral association modules, to overcome the constraints of convolution kernels. Also, we design a factorized architecture search (FAS) framework that involves two independent subprocedures to determine the layer-level operation choices and block-level orders of SSTN. Unlike conventional neural architecture search (NAS) that requires a bilevel optimization of both network parameters and architecture settings, the FAS focuses only on finding out optimal architecture settings to enable a stable and fast architecture search. Extensive experiments conducted on five popular HSI benchmarks demonstrate the versatility of SSTNs over other state-of-the-art (SOTA) methods and justify the FAS strategy. On the University of Houston dataset, SSTN obtains comparable overall accuracy to SOTA methods with a small fraction (1.2%) of multiply-and-accumulate operations compared to a strong baseline spectral–spatial residual network (SSRN). Most importantly, SSTNs outperform other SOTA networks using only 1.2% or fewer MACs of SSRNs on the Indian Pines, the Kennedy Space Center, the University of Pavia, and the Pavia Center datasets.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tgrs.2021.3115699

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 7 references

Research works printed but not linked: 41

  1. 10.1109/TGRS.2017.2755542 · DOI · Paper page
  2. 10.1109/TGRS.2008.2002577 · DOI · Paper page
  3. 10.1109/TGRS.2011.2162649 · DOI · Paper page
  4. 10.1109/MSP.2013.2278992 · DOI · Paper page
  5. 10.1109/TGRS.2008.922034 · DOI · Paper page
  6. 10.1109/TGRS.2004.831865 · DOI · Paper page
  7. 10.1109/TGRS.2010.2048116 · DOI · Paper page
  8. 10.1109/TGRS.2012.2201730 · DOI · Paper page
  9. 10.1109/JPROC.2012.2229082 · DOI · Paper page
  10. 10.1109/CVPR.2015.7298965 · DOI · Paper page
  11. 10.1109/TPAMI.2015.2389824 · DOI · Paper page
  12. 10.1109/TGRS.2016.2616355 · DOI · Paper page
  13. 10.1109/TGRS.2019.2951160 · DOI · Paper page
  14. 10.1109/JSTARS.2020.3011257 · doi:10.1109/jstars.2020.3011257
  15. 10.1016/j.patcog.2017.11.024 · DOI
  16. 10.1109/TGRS.2016.2616489 · DOI
  17. 10.1109/TCYB.2019.2915094 · DOI · Paper page
  18. 10.3390/rs11080963 · DOI · Paper page
  19. 10.1109/LGRS.2016.2553699 · doi:10.1109/lgrs.2016.2553699
  20. 10.1109/TGRS.2019.2934760 · DOI · Paper page
  21. 10.1109/TGRS.2019.2910603 · DOI · Paper page
  22. Vaswani, 2017, Attention is all you need
  23. 10.3390/rs11020159 · DOI · Paper page
  24. 10.3390/rs11111307 · DOI · Paper page
  25. 10.1109/TGRS.2019.2933609 · DOI · Paper page
  26. 10.1109/TGRS.2020.2994057 · DOI · Paper page
  27. Liu, 2018, DARTS: Differentiable architecture search
  28. 10.1109/TGRS.2020.3020424 · DOI
  29. 10.1109/TGRS.2020.2976694 · DOI
  30. 10.1109/TGRS.2014.2358934 · DOI · Paper page
  31. 10.1109/MGRS.2016.2540798 · DOI · Paper page
  32. 10.1109/MGRS.2016.2616418 · DOI · Paper page
  33. 10.1109/JSTARS.2016.2517204 · DOI · Paper page
  34. 10.1109/TGRS.2016.2636241 · DOI · Paper page
  35. 10.1109/TIP.2018.2799324 · DOI · Paper page
  36. 10.1109/MGRS.2018.2854840 · DOI · Paper page
  37. 10.1109/ICCV.2019.00926 · DOI · Paper page
  38. 10.1109/CVPR42600.2020.01308 · DOI · Paper page
  39. 10.1109/JSTARS.2014.2305441 · DOI · Paper page
  40. 10.1109/TGRS.2016.2584107 · DOI · Paper page
  41. 10.1109/LGRS.2019.2911322 · DOI

Cited by

See all 241

Metadata

Authors
Zhong, Z., Li, Y., Ma, L., Li, J., & Zheng, W.-S.
Venue
IEEE Transactions on Geoscience and Remote Sensing
Published
2022
Volume
60
Pages
1-15
ISSN
  • 0196-2892 (ISSN-L)
  • 1558-0644
OpenAlex
W3205965083
Cited by
241
References
7
FWCI
16.68
Type
journal article
Language
en
Open access
closed
Funders
  • China Postdoctoral Science Foundation (2020TQ0372, 2020M672964)
  • Guangdong Natural Science Foundation (2021A1515011843)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Spectral–Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework. https://app.cochat.ai/papers/10.1109/tgrs.2021.3115699
The paper
Zhong, Z., Li, Y., Ma, L., Li, J., & Zheng, W.-S. (2022). Spectral–Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework. IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/tgrs.2021.3115699

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.