Pith Number

pith:5EGDK5I2

pith:2025:5EGDK5I2ZIABKJZHAP7H3XNXYC

not attested not anchored not stored refs resolved

SpectralTrain: A Universal Framework for Hyperspectral Image Classification

Jiarui Zhao, Liping Yu, Meihua Zhou, Nan Wan, Ruiguo Hu, Wai Kin Fung, Wenzhuo Liu, Xinyu Tong

SpectralTrain speeds hyperspectral image model training by 2-7x using curriculum learning and PCA spectral reduction while keeping accuracy close to full training.

arxiv:2511.16084 v2 · 2025-11-20 · cs.CV · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5EGDK5I2ZIABKJZHAP7H3XNXYC}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

SpectralTrain enables efficient learning of spectral-spatial patterns at significantly reduced computational costs, delivering consistent 2-7x training speedups with small-to-moderate accuracy deltas across backbones on three benchmark datasets.

C2weakest assumption

That PCA-based spectral downsampling combined with a curriculum schedule preserves essential information for accurate classification while the gradual complexity increase reliably improves learning efficiency over standard training.

C3one line summary

SpectralTrain is a universal training framework that combines curriculum learning and PCA spectral downsampling to deliver 2-7x faster training for hyperspectral image classification across multiple backbones and datasets with only small accuracy trade-offs.

References

48 extracted · 48 resolved · 0 Pith anchors

[1] IEEE Transactions on Geoscience and Remote Sensing (2025) 2025

[2] El-Gabri, A.R., Aly, H.A., Ghoniemy, T.S.,et al.: DLRA-Net: Deep local residual attention network with contextual refinement for spectral super- resolution. Int. J. Comput. Vis.133, 1499–1531 (2025) h 2025

[3] Recent advances in techniques for hyperspectral image processing 2009 · doi:10.1016/j.rse.2007.07.028

[4] IEEE Signal processing magazine19(1), 17–28 (2002) 2002

[5] ISPRS Journal of Photogrammetry and Remote Sensing158, 279–317 (2019) 29 2019

Receipt and verification

First computed	2026-05-18T03:09:33.121420Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e90c35751aca0015272703fe7dddb7c088809b246aa035e04f0439714202c9bc

Aliases

arxiv: 2511.16084 · arxiv_version: 2511.16084v2 · doi: 10.48550/arxiv.2511.16084 · pith_short_12: 5EGDK5I2ZIAB · pith_short_16: 5EGDK5I2ZIABKJZH · pith_short_8: 5EGDK5I2

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/5EGDK5I2ZIABKJZHAP7H3XNXYC \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: e90c35751aca0015272703fe7dddb7c088809b246aa035e04f0439714202c9bc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "384ee8eaa77e56b1163d5e5b4539d3b0991b4b16081787f5a0e0c8a36aabe43f",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-11-20T06:19:26Z",
    "title_canon_sha256": "af8e378f9091089da4c2bf8831cb0a2bbcd30e44b6fbb1fbecbfd613a5c376ba"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.16084",
    "kind": "arxiv",
    "version": 2
  }
}