Papers › MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

18 Jul 2023arXiv:2307.09361archive 2025-07-28

Spyros Gidaris, Andrei Bursuc, Oriane Simeoni, Antonin Vobecky, Nikos Komodakis, Matthieu Cord, Patrick Pérez

Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual reasoning properties, e.g., using masked image modeling strategies, or invariance to image perturbations, e.g., with contrastive methods. In this work, we propose a single-stage and standalone method, MOCA, which unifies both desired properties using novel mask-and-predict objectives defined with high-level features (instead of pixel-level details). Moreover, we show how to effectively employ both learning paradigms in a synergistic and computation-efficient way. Doing so, we achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols with a training that is at least 3 times faster than prior methods. We provide the implementation code at https://github.com/valeoai/MOCA.

PaperPDFCodeCode Syntology ran

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 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (12 with no instrument failure; 1 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.

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. 1 of the 13 samples that ran has no recorded date.

valeoai/moca officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 15 samples, 13 ran (1 instrument-failed) · 2 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

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran; the contract check could not run
9ran
2unverified

Licence: 15 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 valeoai/moca. “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.

valeoai/moca official repository 15 samples, 13 ran (1 instrument-failed) · 2 unverified
adjust_learning_rate in 125 papers eval_finetune.py ran · honoured contract no licence file found · pointer only · bd3578806ecf5ac2 · report fixture: signature optimizer:SGD/0/?, epoch:int/0/int, args:Args/0/? · returned float · level recorded, date not recorded
all_reduce_mean in 27 papers util/misc.py ran · honoured contract fingerprinted no licence file found · pointer only · 3dc19396537db789 · report fixture: signature x:float/0/float · returned float · level recorded 2026-09-24
buildLabelIndex in 8 papers util/data_utils.py ran fingerprinted licence not identified · pointer only · 57889d72f516d105 · report fixture: signature labels:list/1/int · returned dict · level recorded 2026-09-24
build_dataset in 151 papers eval_finetune.py ran licence not identified · pointer only · 9d24fe78509853ec · report fixture: signature is_train:bool/0/bool, args:Args/0/? · returned ImageFolder · level recorded 2026-09-24
build_transform in 170 papers eval_finetune.py ran licence not identified · pointer only · ae21f98447467f18 · report fixture: signature is_train:bool/0/bool, args:SimpleNamespace/0/? · returned Compose · level recorded 2026-09-24
concat_all_gather in 141 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input
util/misc.py ran fingerprinted licence not identified · pointer only · 3c7b9c20481fa62f · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind float, dtype float32
util/model_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 5c8ea92d43ead77d · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers util/model_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · 77e8a3ac46f3afec · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-24
knn_classifier in 16 papers util/knn_utils.py ran licence not identified · pointer only · d5a2c7c5c6f12965 · report fixture: signature train_features:Tensor/2/float, train_labels:Tensor/1/int, test_features:Tensor/2/float, test_labels:Tensor/1/int, k:int/0/int, T:float/0/float, num_classes:int/0/int, num_chunks:int/0/int, euclidean:bool/0/bool · returned tuple · level recorded 2026-09-24
prepare_knn_imagenet_datasets util/data_utils.py ran licence not identified · pointer only · d9dc385a3c9e906e · report fixture: signature data_path:str/0/str, global_rank:int/0/int, num_tasks:int/0/int, input_size:int/0/int, subset:NoneType/0/?, batch_size:int/0/int, num_workers:int/0/int, pin_mem:bool/0/bool · returned tuple · level recorded 2026-09-24
preprocess_embeddings eval_lowshot_logistic.py ran fingerprinted licence not identified · pointer only · a532283a514e44c5 · report fixture: signature embs:Tensor/2/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-24
reduce_all util/misc.py ran fingerprinted licence not identified · pointer only · 3aa8a268d0817a99 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
subset_of_ImageNet_train_split util/data_utils.py ran licence not identified · pointer only · 3fcd69d9585e3775 · report fixture: signature dataset_train:MockImageNetDataset/0/?, subset:int/0/int · returned MockImageNetDataset · level recorded 2026-09-24
get_2d_sincos_pos_embed_from_grid in 140 papers util/model_utils.py unverified no licence file found · pointer only · 2884deadbb637c3e · report
init_data in 8 papers eval_lowshot_logistic.py unverified licence not identified · pointer only · 6ce1dce0cfb1a538 · report

Tasks

Representation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

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

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