Papers › K-LITE: Learning Transferable Visual Models with External Knowledge

K-LITE: Learning Transferable Visual Models with External Knowledge

20 Apr 2022arXiv:2204.09222archive 2025-07-28

Sheng Shen, Chunyuan Li, Xiaowei Hu, Jianwei Yang, Yujia Xie, Pengchuan Zhang, Zhe Gan, Lijuan Wang, Lu Yuan, Ce Liu, Kurt Keutzer, Trevor Darrell, Anna Rohrbach, Jianfeng Gao

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability of the learned visual models, due to the broad concept coverage achieved via large-scale data collection process. Alternatively, we argue that learning with external knowledge is a promising way which leverages a much more structured source of supervision and offers sample efficiency. We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts. In evaluation, the text is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models. We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively. The proposed knowledge-augmented models show significant improvement in transfer learning performance over existing methods. Our code is available at https://github.com/microsoft/klite.

PaperPDFCodeCode 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 10 code samples harvested from 1 repository linked to this paper: 5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

microsoft/klite mentioned on GitHubpytorchSyntology: 10 samples, 5 ran (0 instrument-failed) · 5 unverified report
microsoft/unicl mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unified Contrastive Learning in Image-Text-Label Space (arXiv:2204.03610; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. 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

10 samples harvested: 5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 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 · violated contract
4ran
5unverified

Licence: 0 of the 10 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/klite. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

microsoft/klite community (archive-listed) 10 samples, 5 ran (0 instrument-failed) · 5 unverified
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
model/model.py ran MIT (permissive) · 5913171a402effd1 · report fixture: returned PatchEmbed · level recorded 2026-09-22
PatchMerging in 31 papers model/model.py ran MIT (permissive) · 89e08495ccdd55f4 · report fixture: returned PatchMerging · level recorded 2026-09-22
SwinTransformerBlock in 35 papers model/model.py ran MIT (permissive) · 5a5551bec22c5f90 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
WindowAttention in 50 papers model/model.py ran MIT (permissive) · 44721c30a2563ec1 · report fixture: returned WindowAttention · level recorded 2026-09-22
is_lang_encoder model/model.py ran · violated contract MIT (permissive) · 253f375438a3b31d · report fixture: signature model_name:str/0/str · returned bool · level recorded 2026-09-22
BasicLayer in 56 papers model/model.py unverified MIT (permissive) · 30fb736aaa42b89d · report
KLITEModel model/model.py unverified MIT (permissive) · 96a6b788f6e04b42 · report
SwinTransformer in 15 papers model/model.py unverified MIT (permissive) · 5817ae83cc9df84f · report
build_tokenizer in 19 papers model/model.py unverified MIT (permissive) · d7ee228866431711 · report
lang_encoders model/model.py unverified MIT (permissive) · 25812f971a96b8f8 · report

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 K-LITE (graph method: K-LITE). 13 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. KLITEModel entry · level 0 · unverified · 96a6b788f6e04b42
  2. build_tokenizer helper · level 0 · unverified · d7ee228866431711
  3. BasicLayer helper · level 0 · unverified · 30fb736aaa42b89d
  4. Mlp helper · level 1 · ran · 86db5e5160400425
  5. PatchEmbed helper · level 1 · ran · 5913171a402effd1
  6. PatchMerging helper · level 1 · ran · 89e08495ccdd55f4
  7. SwinTransformer helper · level 0 · unverified · 5817ae83cc9df84f
  8. SwinTransformerBlock helper · level 1 · ran · 5a5551bec22c5f90
  9. WindowAttention helper · level 1 · ran · 44721c30a2563ec1
  10. is_lang_encoder helper · level 1 · ran · violated contract · 253f375438a3b31d
  11. lang_encoders helper · level 0 · unverified · 25812f971a96b8f8
  12. window_partition helper · level 2 · ran; the contract check could not run · 144d10b49baeb8a6
  13. window_reverse helper · level 1 · ran · our draft was wrong · 61bf152e6a42a184

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="2204.09222") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

BenchmarkingDescriptiveImage ClassificationObject DetectionTransfer Learningimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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