Papers › data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

7 Feb 2022Preprint 2022 1arXiv:2202.03555archive 2025-07-28

Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, Michael Auli

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches.

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="2202.03555")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: community (archive-listed): 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

pytorch/fairseq officialpytorch report
AryanShekarlaban/data2vec-pytorch mentioned on GitHubpytorchMIT report
Guillem96/data2vec-vision mentioned on GitHubpytorchGPL-3.0 report
aau-es-ml/ssl_noise-robust_kws mentioned on GitHubpytorch report
ashutosh1919/data2vec-pytorch mentioned on GitHubpytorchMIT report
gatech-eic/s3-router mentioned on GitHubpytorchMIT report
holgerbovbjerg/data2vec-kws mentioned on GitHubpytorchMIT report
SPEECHCOG/data2vec_maiju pytorchNOASSERTION 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

6 samples harvested; 0 ran; 0 honoured the contract we drafted; 6 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.

6unverified

Licence: 0 of the 6 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 holgerbovbjerg/data2vec-kws. “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.

compute_var holgerbovbjerg/data2vec-kws/data2vec/data2vec_utils/trainer.py community (archive-listed) unverified MIT (permissive) · 2aa6bb5bf9a3cec5 · report
generate_masked_tensor holgerbovbjerg/data2vec-kws/data2vec/masking.py community (archive-listed) unverified MIT (permissive) · 098fbbfa32b9e2f9 · report
get_config holgerbovbjerg/data2vec-kws/config_parser.py community (archive-listed) unverified MIT (permissive) · d203ddadc113d9d6 · report
get_train_val_test_split holgerbovbjerg/data2vec-kws/utils/dataset.py community (archive-listed) unverified MIT (permissive) · 6a3668fb4b8c0404 · report
kwt_from_name holgerbovbjerg/data2vec-kws/models/KWT.py community (archive-listed) unverified MIT (permissive) · e8760411566b7fe1 · report
variance_loss holgerbovbjerg/data2vec-kws/data2vec/data2vec_utils/trainer.py community (archive-listed) unverified MIT (permissive) · 4ad2bd1c77f9444c · report

Tasks

Image ClassificationLinguistic AcceptabilityNatural Language InferenceNatural Language UnderstandingParaphrase IdentificationSelf-Supervised LearningSpeech Recognitionimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet data2vec (ViT-H) Number of params 656M #135 of 1060 Archive leaderboard report
Image Classification ImageNet data2vec (ViT-H) Top 1 Accuracy 86.6% #135 of 1060 Archive leaderboard report
Linguistic Acceptability CoLA data2vec Accuracy 60.3% #30 of 43 Archive leaderboard report
Natural Language Inference QNLI data2vec Accuracy 91.1% #30 of 43 Archive leaderboard report
Natural Language Inference RTE data2vec Accuracy 69.9% #55 of 90 Archive leaderboard report
Paraphrase Identification Quora Question Pairs data2vec Accuracy 92.4 #16 of 31 Archive leaderboard report
Speech Recognition LibriSpeech test-other data2vec Word Error Rate (WER) 3.7 #12 of 53 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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