Pith Number

pith:OVA5G7E5

pith:2026:OVA5G7E5S5V7ZY5YVLBA7WRQ76

not attested not anchored not stored refs resolved

Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks

AntonioManuel Lopez Pena, Danna Xue, JoseLuis Gomez Zurita, Yachan Guo, Yi Xiao

Label-free metrics identify complementary VFM pairs for fusion that boosts dense prediction performance.

arxiv:2605.16864 v1 · 2026-05-16 · 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{OVA5G7E5S5V7ZY5YVLBA7WRQ76}

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

Our model shows consistent performance gains across multiple dense prediction tasks compared with the baselines, with better object-level semantics and more accurately localized boundaries.

C2weakest assumption

The label-free metrics for Structural Coherence and Edge Fidelity in feature space can reliably identify which VFM encoders are complementary and worth fusing, without any task-specific labels or supervision.

C3one line summary

A label-free metric-guided fusion of complementary features from visual foundation models yields consistent gains in dense prediction tasks with improved object semantics and boundary localization.

References

47 extracted · 47 resolved · 3 Pith anchors

[1] Improving vision transformers by revisiting high-frequency components 2022

[2] Do computer vision foundation models learn the low- level characteristics of the human visual system? InCVPR,

[3] Emerg- ing properties in self-supervised vision transformers 2021

[4] Sam-adapter: Adapting segment any- thing in underperformed scenes 2023

[5] Vision transformer adapter for dense predictions 2023

Receipt and verification

First computed	2026-05-20T00:03:27.060116Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7541d37c9d976bfce3b8aac20fda30ff8adf660aec055c7bf966d66cb0a56929

Aliases

arxiv: 2605.16864 · arxiv_version: 2605.16864v1 · doi: 10.48550/arxiv.2605.16864 · pith_short_12: OVA5G7E5S5V7 · pith_short_16: OVA5G7E5S5V7ZY5Y · pith_short_8: OVA5G7E5

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/OVA5G7E5S5V7ZY5YVLBA7WRQ76 \
  | 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: 7541d37c9d976bfce3b8aac20fda30ff8adf660aec055c7bf966d66cb0a56929

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "73ed6cedc7a219aaffa5581125df0133ed2b2b1034812eee25b9bed0becda14a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T07:55:41Z",
    "title_canon_sha256": "91fbd7517f89c1ab0f00235d5633fbf9e943d8693dc96b10b965bbe06d1ec3db"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16864",
    "kind": "arxiv",
    "version": 1
  }
}