Pith Number

pith:WYOEE2ZB

pith:2021:WYOEE2ZBWHIBD7DAZTWK74NMIU

not attested not anchored not stored refs resolved

BEiT: BERT Pre-Training of Image Transformers

Furu Wei, Hangbo Bao, Li Dong, Songhao Piao

BEiT pre-trains vision transformers by recovering discrete visual tokens from masked image patches, reaching 83.2% ImageNet-1K accuracy.

arxiv:2106.08254 v2 · 2021-06-15 · 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{WYOEE2ZBWHIBD7DAZTWK74NMIU}

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

base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%).

C2weakest assumption

The discrete visual tokens produced by the separate tokenizer are assumed to form a sufficiently rich and stable target for the masked modeling objective; if the tokenizer collapses or captures only low-level statistics the pre-training signal would be weak.

C3one line summary

BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.

References

23 extracted · 23 resolved · 8 Pith anchors

[1] UniLMv2: Pseudo- masked language models for uniﬁed language model pre-training 2020

[2] Improved Baselines with Momentum Contrastive Learning 2003 · arXiv:2003.04297

[3] Exploring simple siamese representation learning 2011

[4] A Simple Framework for Contrastive Learning of Visual Representations 2002 · arXiv:2002.05709

[5] Emerging Properties in Self-Supervised Vision Transformers · arXiv:2104.14294

Formal links

2 machine-checked theorem links

Cited by

74 papers in Pith

HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision

Contrastive Action-Image Pre-training for Visuomotor Control

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation

DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning

Receipt and verification

First computed	2026-07-05T04:54:14.716257Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b61c426b21b1d011fc60ccecaff1ac453976a93258d1f258891638c6bc541e33

Aliases

arxiv: 2106.08254 · arxiv_version: 2106.08254v2 · doi: 10.48550/arxiv.2106.08254 · pith_short_12: WYOEE2ZBWHIB · pith_short_16: WYOEE2ZBWHIBD7DA · pith_short_8: WYOEE2ZB

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/WYOEE2ZBWHIBD7DAZTWK74NMIU \
  | 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: b61c426b21b1d011fc60ccecaff1ac453976a93258d1f258891638c6bc541e33

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1f3e8325d4af081ae4fa89ef02f1e4adc9ee86873be729eb2882fb5efb7f5e21",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-06-15T16:02:37Z",
    "title_canon_sha256": "3b15a271f12d9e3e7cee88cd64608d27a190306c89c598295a2bb6c1c3b42777"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2106.08254",
    "kind": "arxiv",
    "version": 2
  }
}