Papers › iBOT: Image BERT Pre-Training with Online Tokenizer

iBOT: Image BERT Pre-Training with Online Tokenizer

15 Nov 2021arXiv:2111.07832archive 2025-07-28

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

The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces. In this work, we study masked image modeling (MIM) and indicate the advantages and challenges of using a semantically meaningful visual tokenizer. We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer. Specifically, we perform self-distillation on masked patch tokens and take the teacher network as the online tokenizer, along with self-distillation on the class token to acquire visual semantics. The online tokenizer is jointly learnable with the MIM objective and dispenses with a multi-stage training pipeline where the tokenizer needs to be pre-trained beforehand. We show the prominence of iBOT by achieving an 82.3% linear probing accuracy and an 87.8% fine-tuning accuracy evaluated on ImageNet-1K. Beyond the state-of-the-art image classification results, we underline emerging local semantic patterns, which helps the models to obtain strong robustness against common corruptions and achieve leading results on dense downstream tasks, eg., object detection, instance segmentation, and semantic segmentation.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2111.07832")

Code

Syntology Ran 0 of 1 code samples harvested from 1 repository linked to this paper; 1 has no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bytedance/ibot officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bytedance/ibot. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

knn_classifier bytedance/ibot/evaluation/eval_knn.py official repository unverified Apache-2.0 (permissive) · 14b1b82d605701ac · report

Tasks

Image ClassificationInstance SegmentationLanguage ModelingLanguage ModellingMasked Language ModelingObject DetectionSelf-Supervised Image ClassificationSemantic SegmentationSemi-Supervised Image ClassificationUnsupervised Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev iBOT (ViT-B/16) mask AP 44.2 #45 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev iBOT (ViT-S/16) mask AP 42.6 #53 of 112 Archive leaderboard report
Object Detection COCO test-dev iBOT (ViT-B/16) box mAP 51.2 #84 of 225 Archive leaderboard report
Object Detection COCO test-dev iBOT (ViT-S/16) box mAP 49.4 #97 of 225 Archive leaderboard report
Self-Supervised Image Classification ImageNet iBOT (ViT-L/16) (IN22k) Number of Params 307M #11 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iBOT (ViT-L/16) (IN22k) Top 1 Accuracy 82.3% #11 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iBOT (ViT-L/16) Number of Params 307M #16 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet iBOT (ViT-L/16) Top 1 Accuracy 81.3% #16 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT(ViT-L/16, 512) Number of Params 307M #8 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT(ViT-L/16, 512) Top 1 Accuracy 87.8% #8 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT(ViT-L/16) Number of Params 307M #12 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT(ViT-L/16) Top 1 Accuracy 86.6% #12 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-L/16) Number of Params 307M #26 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-L/16) Top 1 Accuracy 84.8% #26 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-B/16) Number of Params 85M #31 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-B/16) Top 1 Accuracy 84.4% #31 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-B/16) Number of Params 85M #39 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) iBOT (ViT-B/16) Top 1 Accuracy 84.0% #39 of 65 Archive leaderboard report
Semantic Segmentation ADE20K iBOT (ViT-B/16) Validation mIoU 50.0 #122 of 235 Archive leaderboard report
Semantic Segmentation ADE20K iBOT (ViT-S/16) Validation mIoU 45.4 #191 of 235 Archive leaderboard report
Semantic Segmentation ADE20K iBOT (ViT-B/16) (linear head) Validation mIoU 38.3 #223 of 235 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data iBOT (ViT-S/16) Top 1 Accuracy 61.9% #37 of 65 Archive leaderboard report
Unsupervised Image Classification ImageNet iBOT (ViT-S/16) ARI 32.8 #4 of 9 Archive leaderboard report
Unsupervised Image Classification ImageNet iBOT (ViT-S/16) Accuracy (%) 43.4 #4 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections