Pith Number

pith:I3SUNKSA

pith:2026:I3SUNKSALH4YUYZPDPTIMEQBMV

not attested not anchored not stored refs resolved

Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet

Enyi Li, Jinchao Liu, Margarita Osadchy, Xin Niu, Yan Wang, Yongchun Fang

A compact encoder-decoder network learns modality-agnostic representations while retaining identity-related information.

arxiv:2605.16887 v1 · 2026-05-16 · cs.CV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{I3SUNKSALH4YUYZPDPTIMEQBMV}

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

We proposed a compact encoder-decoder neural module (cmUNet) to learn modality-agnostic representations while retaining identity-related information. This is achieved through cross-modality transformation and in-modality reconstruction, enhanced by an adversarial/perceptual loss which encourages indistinguishability of representations in the original sample space.

C2weakest assumption

The assumption that cross-modality transformation combined with in-modality reconstruction and adversarial loss can retain discriminant identity information without the losses of prior distributional alignment or transfer methods, and that robustness to occlusions serves as a reliable indicator of successful modality-gap bridging.

C3one line summary

cmUNet learns modality-agnostic representations via cross-modality transformation and in-modality reconstruction with adversarial loss, enabling MarrNet to achieve superior cross-modality matching on spectrum, re-identification, and face recognition tasks.

References

82 extracted · 82 resolved · 0 Pith anchors

[1] Matching forensic sketches to mug shot photos, 2011

[2] Composite sketch recognition via deep network - a transfer learning approach, 2015

[3] Simultaneous local binary feature learning and encoding for homogeneous and heterogeneous face recog- nition, 1979

[4] Face sketch synthesis and recognition, 2003

[5] A nonlinear approach for face sketch synthesis and recognition, 2005

Receipt and verification

First computed	2026-05-20T00:03:28.405104Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

46e546aa4059f98a632f1be68612016578f818711a6e0d003168d786a976c63c

Aliases

arxiv: 2605.16887 · arxiv_version: 2605.16887v1 · doi: 10.48550/arxiv.2605.16887 · pith_short_12: I3SUNKSALH4Y · pith_short_16: I3SUNKSALH4YUYZP · pith_short_8: I3SUNKSA

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/I3SUNKSALH4YUYZPDPTIMEQBMV \
  | 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: 46e546aa4059f98a632f1be68612016578f818711a6e0d003168d786a976c63c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d1bea2e7509096c03cad3bdee49dfff5081df854334bc037ee39f6fcbe357a57",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T09:00:54Z",
    "title_canon_sha256": "bc04160b356ad1c8ebf64e91c06c0e24dffffb0de5e3c0418820726c613b7687"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16887",
    "kind": "arxiv",
    "version": 1
  }
}