Papers › UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

23 Nov 2021arXiv:2111.12085archive 2025-07-28

Zhengyuan Yang, Zhe Gan, JianFeng Wang, Xiaowei Hu, Faisal Ahmed, Zicheng Liu, Yumao Lu, Lijuan Wang

We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text description and align predicted words with object regions. To achieve this, models must generate desired text and box outputs together, and meanwhile indicate the alignments between words and boxes. In contrast to existing solutions that use multiple separate modules for different outputs, UniTAB represents both text and box outputs with a shared token sequence, and introduces a special <obj> token to naturally indicate word-box alignments in the sequence. UniTAB thus could provide a more comprehensive and interpretable image description, by freely grounding generated words to object regions. On grounded captioning, UniTAB presents a simpler solution with a single output head, and significantly outperforms state of the art in both grounding and captioning evaluations. On general VL tasks that have different desired output formats (i.e., text, box, or their combination), UniTAB with a single network achieves better or comparable performance than task-specific state of the art. Experiments cover 7 VL benchmarks, including grounded captioning, visual grounding, image captioning, and visual question answering. Furthermore, UniTAB's unified multi-task network and the task-agnostic output sequence design make the model parameter efficient and generalizable to new tasks.

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="2111.12085")

Code

Syntology Ran 6 of 15 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong.

By repository: official repository: 15 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/UniTAB officialmentioned in papermentioned on GitHubpytorchMIT 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

15 samples harvested; 6 ran; 1 honoured the contract we drafted; 9 have 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
5ran · our draft was wrong
9unverified

Licence: 0 of the 15 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/UniTAB. “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.

convert_to_xywh microsoft/UniTAB/datasets/coco_eval.py official repository ran · honoured contract fingerprinted MIT (permissive) · f31a58bf6457ced5 · report
cook_refs microsoft/UniTAB/cococapeval/cider/cider_scorer.py official repository ran · our draft was wrong MIT (permissive) · 4c1b107103b7c856 · report
cook_test microsoft/UniTAB/cococapeval/cider/cider_scorer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 3573c4bc85f65dfd · report
evaluate microsoft/UniTAB/datasets/coco_eval.py official repository ran · our draft was wrong MIT (permissive) · fe0ddcc2d420c9a0 · report
precook microsoft/UniTAB/cococapeval/bleu/bleu_scorer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · ec4448373d72d636 · report
precook microsoft/UniTAB/cococapeval/cider/cider_scorer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9560e3e3e41bc1b2 · report
build_position_encoding microsoft/UniTAB/models/position_encoding.py official repository unverified MIT (permissive) · cea3f92defccfb9c · report
build_transformer microsoft/UniTAB/models/transformer_unitab.py official repository unverified MIT (permissive) · 0b02672adf92e20a · report
cook_refs microsoft/UniTAB/cococapeval/bleu/bleu_scorer.py official repository unverified MIT (permissive) · 7586e1d32f7325f7 · report
cook_test microsoft/UniTAB/cococapeval/bleu/bleu_scorer.py official repository unverified MIT (permissive) · 99e54843980299e2 · report
create_positive_map microsoft/UniTAB/datasets/coco.py official repository unverified MIT (permissive) · 5c1b500d83c0cf64 · report
seq2logits microsoft/UniTAB/models/postprocessors.py official repository unverified MIT (permissive) · a3646da4ef0cdb56 · report
target2gtind microsoft/UniTAB/models/unitab.py official repository unverified MIT (permissive) · e4584fdac028654e · report
target2prevind microsoft/UniTAB/models/unitab.py official repository unverified MIT (permissive) · 11cd2a3ee603af97 · report
withbbox_subseq microsoft/UniTAB/models/unitab.py official repository unverified MIT (permissive) · 97aaacff6f0b7fee · report

Tasks

Image CaptioningLanguage ModelingLanguage ModellingObject LocalizationQuestion AnsweringText GenerationVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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