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 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="2206.07643")

Code

Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 0 ran; 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.

microsoft/fiber 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

3 samples harvested; 2 ran; 1 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.

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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

FusionSwinTransformer microsoft/fiber/fine_grained/maskrcnn_benchmark/modeling/backbone/fusion_swin_transformer.py official repository unverified MIT (permissive) · d772fb1ce96f80c5 · report
create_positive_map identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 525b77c721203779 · report
create_positive_map_label_to_token_from_positive_map identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · ea2c188d68558611 · report

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