Pith Number

pith:GBMUKCEF

pith:2026:GBMUKCEFJCF6H6EWSM74QHUWOR

not attested not anchored not stored refs resolved

Rethinking the Good Enough Embedding for Easy Few-Shot Learning

Alper Yilmaz, Michael Karnes

A frozen DINOv2 embedding paired with k-nearest neighbor classification reaches state-of-the-art few-shot accuracy without any fine-tuning.

arxiv:2605.14145 v1 · 2026-05-13 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GBMUKCEFJCF6H6EWSM74QHUWOR}

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

By utilizing a k-Nearest Neighbor classifier on frozen DINOv2-L features, we conduct a layer-wise characterization to identify an optimal feature extraction. We further demonstrate that manifold refinement via PCA and ICA provides a beneficial regularizing effect. Our results across four major benchmarks demonstrate that our approach consistently surpasses sophisticated meta-learning algorithms, achieving state-of-the-art performance.

C2weakest assumption

The assumption that DINOv2 features already form a sufficiently universal and task-agnostic representation so that no task-specific adaptation or learned metric is required; this is invoked when claiming the frozen embedding plus k-NN is 'good enough' for complex tasks.

C3one line summary

Frozen DINOv2-L features with k-NN classification and PCA/ICA refinement achieve state-of-the-art few-shot performance on four benchmarks without any backpropagation or fine-tuning.

References

46 extracted · 46 resolved · 4 Pith anchors

[1] Bateni, P., Goyal, R., Masrani, V., Wood, F., Sigal, L.: Improved few-shot visual classification (2020),https://arxiv.org/abs/1912.03432 2020

[2] Chen, W., Si, C., Zhang, Z., Wang, L., Wang, Z., Tan, T.: Semantic prompt for few-shot image recognition (2023),https://arxiv.org/abs/2303.14123 2023

[3] Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-baseline: Exploring simple meta-learning for few-shot learning (2021),https://arxiv.org/abs/2003.04390 2021

[4] st + 1 K KX k=1 vt k # =E t 2023 · doi:10.1109/iccv51070

[5] In: Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XX 2022 · doi:10.1007/978-3-031-20044-1_19

Receipt and verification

First computed	2026-05-17T23:39:11.638172Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3059450885488be3f896933fc81e9674691a33e6bea940d810484b4fd849ec77

Aliases

arxiv: 2605.14145 · arxiv_version: 2605.14145v1 · doi: 10.48550/arxiv.2605.14145 · pith_short_12: GBMUKCEFJCF6 · pith_short_16: GBMUKCEFJCF6H6EW · pith_short_8: GBMUKCEF

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/GBMUKCEFJCF6H6EWSM74QHUWOR \
  | 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: 3059450885488be3f896933fc81e9674691a33e6bea940d810484b4fd849ec77

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dd99c6eff52e9a35f8d1918b5ef78dab10ff93af0bee87c45d0cacd598ac9476",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T21:52:05Z",
    "title_canon_sha256": "7c35b365c4225306ce8c4d8af3fbb23cc07acf09c84a677e007cd58fb8a1f88e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14145",
    "kind": "arxiv",
    "version": 1
  }
}