pith:B5P5PCPW
CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
Unfolding the Flury-Gautschi algorithm into neural layers lets common principal component analysis discover domain-invariant subspaces directly inside end-to-end training.
arxiv:2605.05136 v3 · 2026-05-06 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{B5P5PCPWMR36CPRBJ5FFSCCG5Z}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on four standard DG benchmarks demonstrate that CPCANet achieves state-of-the-art (SOTA) performance in zero-shot transfer. Moreover, CPCANet is architecture-agnostic and requires no dataset-specific tuning.
That the common principal components discovered by the unfolded Flury-Gautschi algorithm represent truly domain-invariant features that remain useful for the downstream task without losing critical information.
CPCANet deep-unfolds Common PCA to learn domain-invariant subspaces, achieving state-of-the-art zero-shot domain generalization on standard benchmarks.
Receipt and verification
| First computed | 2026-06-09T01:05:18.764310Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
0f5fd789f66477e13e214f4a590846ee7452ec9aa313ee6475e77eed46856779
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/B5P5PCPWMR36CPRBJ5FFSCCG5Z \
| 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: 0f5fd789f66477e13e214f4a590846ee7452ec9aa313ee6475e77eed46856779
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "8031470b3c6dc9b3e575efb0f1c883dd249f497c44634e4687fd04c887290c11",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-06T17:09:34Z",
"title_canon_sha256": "411668754c7010b38d29a73dd4c891a3f9dae61ba2205434a488cd62286e41d5"
},
"schema_version": "1.0",
"source": {
"id": "2605.05136",
"kind": "arxiv",
"version": 3
}
}