Papers › Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

22 Aug 2022arXiv:2208.10442archive 2025-07-28

Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, Furu Wei

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

microsoft/unilm officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training (arXiv:2002.12804; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified), DeepNet: Scaling Transformers to 1,000 Layers (arXiv:2203.00555; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
lyan62/data-curation mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

AllCross-Modal RetrievalImage CaptioningImage ClassificationInstance SegmentationLanguage ModelingLanguage ModellingMasked Language ModelingObject DetectionQuestion AnsweringRetrievalSemantic SegmentationVisual Question AnsweringVisual Question Answering (VQA)Visual ReasoningZero-Shot Cross-Modal Retrievalimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 BEiT-3 Image-to-text R@1 84.8 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 BEiT-3 Image-to-text R@10 98.3 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 BEiT-3 Image-to-text R@5 96.5 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 BEiT-3 Text-to-image R@1 67.2 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 BEiT-3 Text-to-image R@10 87.7 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 BEiT-3 Text-to-image R@5 92.8 #3 of 36 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@1 98.0 #3 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@10 100.0 #3 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@5 100.0 #3 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@1 90.3 #3 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@10 99.5 #3 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@5 98.7 #3 of 27 Archive leaderboard report
Instance Segmentation COCO test-dev BEiT-3 mask AP 54.8 #6 of 112 Archive leaderboard report
Object Detection COCO test-dev BEiT-3 box mAP 63.7 #14 of 225 Archive leaderboard report
Semantic Segmentation ADE20K BEiT-3 Params (M) 1900 #5 of 235 Archive leaderboard report
Semantic Segmentation ADE20K BEiT-3 Validation mIoU 62.8 #5 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val BEiT-3 mIoU 62.8 #1 of 95 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-dev BEiT-3 Accuracy 84.19 #2 of 56 Archive leaderboard report
Visual Question Answering (VQA) VQA v2 test-std BEiT-3 overall 84.03 #1 of 38 Archive leaderboard report
Visual Reasoning NLVR2 Dev BEiT-3 Accuracy 91.51 #1 of 15 Archive leaderboard report
Visual Reasoning NLVR2 Test BEiT-3 Accuracy 92.58 #1 of 14 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@1 94.9 #2 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@10 100.0 #2 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Image-to-text R@5 99.9 #2 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@1 81.5 #2 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@10 97.8 #2 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k BEiT-3 Text-to-image R@5 95.6 #2 of 22 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