Pith Number

pith:2XX22VJU

pith:2021:2XX22VJUL7SIEBCQF3WFMGTECS

not attested not anchored not stored refs resolved

iBOT: Image BERT Pre-Training with Online Tokenizer

Alan Yuille, Chen Wei, Cihang Xie, Huiyu Wang, Jinghao Zhou, Tao Kong, Wei Shen

iBOT uses a jointly learned online tokenizer for masked image modeling to reach 82.3 percent linear probing accuracy on ImageNet-1K.

arxiv:2111.07832 v3 · 2021-11-15 · 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{2XX22VJUL7SIEBCQF3WFMGTECS}

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 present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer... achieving an 82.3% linear probing accuracy and an 87.8% fine-tuning accuracy evaluated on ImageNet-1K.

C2weakest assumption

The assumption that self-distillation with an online tokenizer can produce semantically meaningful visual tokens without prior pre-training of the tokenizer.

C3one line summary

iBOT achieves 82.3% linear probing accuracy and 87.8% fine-tuning accuracy on ImageNet-1K using masked image modeling with a jointly trained online tokenizer.

References

23 extracted · 23 resolved · 3 Pith anchors

[1] Self-supervised classiﬁcation network

[2] SiT: Self-supervised vision transformer

[3] BEiT: BERT Pre-Training of Image Transformers · arXiv:2106.08254

[4] 10 Published as a conference paper at ICLR 2022 Kaiming He, Georgia Gkioxari, Piotr Doll´ar, and Ross Girshick. Mask R-CNN. In ICCV, 2022

[5] Efﬁcient self-supervised vision transformers for representation learning

Formal links

3 machine-checked theorem links

Cited by

31 papers in Pith

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining

VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection

Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining

CanViT: Toward Active-Vision Foundation Models

Receipt and verification

First computed	2026-05-18T02:42:36.995746Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d5efad55345fe48204502eec561a6414a6779317b3fb51db2e0c3193230934d3

Aliases

arxiv: 2111.07832 · arxiv_version: 2111.07832v3 · doi: 10.48550/arxiv.2111.07832 · pith_short_12: 2XX22VJUL7SI · pith_short_16: 2XX22VJUL7SIEBCQ · pith_short_8: 2XX22VJU

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/2XX22VJUL7SIEBCQF3WFMGTECS \
  | 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: d5efad55345fe48204502eec561a6414a6779317b3fb51db2e0c3193230934d3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6e7728ee498ae978c428082bad3072a8254578a2aac25125ad12a37dae769d5b",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-11-15T15:18:05Z",
    "title_canon_sha256": "c60bc85e27b6e89d8c0f68d113d4613cc285eca8d8a9681eed9b0379dc67c9d8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2111.07832",
    "kind": "arxiv",
    "version": 3
  }
}