Papers › Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

15 Jun 2022NeurIPS 2022 5arXiv:2206.07643archive 2025-07-28

Zi-Yi Dou, Aishwarya Kamath, Zhe Gan, Pengchuan Zhang, JianFeng Wang, Linjie Li, Zicheng Liu, Ce Liu, Yann Lecun, Nanyun Peng, Jianfeng Gao, Lijuan Wang

Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model by inserting cross-attention into the image and text backbones, bringing gains in terms of memory and performance. In addition, unlike previous work that is either only pre-trained on image-text data or on fine-grained data with box-level annotations, we present a two-stage pre-training strategy that uses both these kinds of data efficiently: (i) coarse-grained pre-training based on image-text data; followed by (ii) fine-grained pre-training based on image-text-box data. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection. Using deep multimodal fusion coupled with the two-stage pre-training, FIBER provides consistent performance improvements over strong baselines across all tasks, often outperforming methods using magnitudes more data. Code is available at https://github.com/microsoft/FIBER.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 3 code samples: 1 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 3: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No date is recorded for any of the 2 samples that ran: their levels were written before Syntology's graph kept the date.

microsoft/fiber officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified 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

3 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1unverified

Licence: 2 of the 3 samples 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 microsoft/fiber. 2 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

microsoft/fiber official repository 1 sample, 0 ran · 1 unverified
FusionSwinTransformer fine_grained/maskrcnn_benchmark/modeling/backbone/fusion_swin_transformer.py unverified MIT (permissive) · d772fb1ce96f80c5 · report
Repository not located 2 samples, 2 ran (1 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
create_positive_map in 8 papers repository not located ran · honoured contract licence of this copy not recorded · 525b77c721203779 · report fixture: signature tokenized:MockTokenized/0/?, tokens_positive:list/1/list · returned Tensor · level recorded, date not recorded
create_positive_map_label_to_token_from_positive_map repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · ea2c188d68558611 · report fixture: signature positive_map:Tensor/2/float, plus:int/0/int · returned dict · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FIBER (graph method: FIBER). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. FusionSwinTransformer entry · level 0 · unverified · d772fb1ce96f80c5

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.07643") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Described Object DetectionImage CaptioningImage-text RetrievalObject DetectionPhrase GroundingQuestion AnsweringReferring Expression ComprehensionText RetrievalVisual Question AnsweringVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Described Object Detection Description Detection Dataset FIBER-B Intra-scenario ABS mAP 26.0 #2 of 8 Archive leaderboard report
Described Object Detection Description Detection Dataset FIBER-B Intra-scenario FULL mAP 22.7 #2 of 8 Archive leaderboard report
Described Object Detection Description Detection Dataset FIBER-B Intra-scenario PRES mAP 21.5 #2 of 8 Archive leaderboard report
Object Detection COCO-O FIBER-B (Swin-B) Average mAP 33.7 #12 of 45 Archive leaderboard report
Object Detection COCO-O FIBER-B (Swin-B) Effective Robustness 11.43 #12 of 45 Archive leaderboard report
Phrase Grounding Flickr30k Entities Dev Fiber-B R@1 87.1 #1 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Dev Fiber-B R@10 97.4 #1 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Dev Fiber-B R@5 96.1 #1 of 3 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test FIBER-B R@1 87.4 #2 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test FIBER-B R@10 97.6 #2 of 18 Archive leaderboard report
Phrase Grounding Flickr30k Entities Test FIBER-B R@5 96.4 #2 of 18 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.

Methods

Test

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