Pith Number

pith:NKI7EUV6

pith:2026:NKI7EUV6VEL66QEZOIK7WNJXXR

not attested not anchored not stored refs resolved

Weakly Supervised Segmentation as Semantic-Based Regularization

Andrei-Bogdan Florea, Jaron Maene, Stefano Colamonaco

Differentiable fuzzy logic encodes weak annotations as continuous constraints to fine-tune SAM and generate higher-quality pseudo-labels for segmentation.

arxiv:2605.13674 v1 · 2026-05-13 · 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{NKI7EUV6VEL66QEZOIK7WNJXXR}

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

Experiments on Pascal VOC 2012 and the REFUGE2 optic disc/cup segmentation dataset show that our logic-guided fine-tuning yields higher-quality pseudo-labels, leading to state-of-the-art segmentation accuracy that often exceeds densely supervised baselines.

C2weakest assumption

That differentiable fuzzy logic can reliably encode heterogeneous weak annotations and domain priors as continuous constraints without introducing systematic biases or requiring dataset-specific tuning that undermines generalization.

C3one line summary

Differentiable fuzzy logic constraints fine-tune SAM to generate higher-quality pseudo-labels, enabling a second-stage model to reach state-of-the-art weakly supervised segmentation on Pascal VOC and REFUGE2, sometimes beating dense supervision.

References

60 extracted · 60 resolved · 2 Pith anchors

[1] In: Proceedings of the IEEE conference on computer vision and pattern recognition 2018

[2] Segdiff: Image segmentation with diffusion proba- bilistic models 2021

[3] Artificial Intelligence303, 103649 (2022) 2022

[4] In: 2025 International Joint Conference on Neural Networks (IJCNN) 2025

[5] TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation 2021 · arXiv:2102.04306

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

sLTN: Structural Logic Tensor Networks

Receipt and verification

First computed	2026-05-18T02:44:17.125029Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6a91f252bea917ef40997215fb3537bc4f83ebc626e5943ce83b9e9b322febfb

Aliases

arxiv: 2605.13674 · arxiv_version: 2605.13674v1 · doi: 10.48550/arxiv.2605.13674 · pith_short_12: NKI7EUV6VEL6 · pith_short_16: NKI7EUV6VEL66QEZ · pith_short_8: NKI7EUV6

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/NKI7EUV6VEL66QEZOIK7WNJXXR \
  | 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: 6a91f252bea917ef40997215fb3537bc4f83ebc626e5943ce83b9e9b322febfb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "894acfb7638cd451ab8ece274a4c757e53fb92c9863cc688be977ce30a249101",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T15:33:27Z",
    "title_canon_sha256": "1e7fdc89fb9f603452177bb11c441726f52e4b8ba54472ba801fee0610f973f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13674",
    "kind": "arxiv",
    "version": 1
  }
}