Papers › Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.
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):
get_harvested_code_for_paper(arxiv_id="2006.09882")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2006.09882", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2006.09882")
Code
The archive's official repository (facebookresearch/swav) was not harvested; the 17 samples below come from 4 community repositories.
Syntology 17 code samples harvested from 4 repositories linked to this paper: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 17 samples from 4 repositories, 13 ran (6 with no instrument failure; 7 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 10 of its repositories that Syntology harvested for other papers:
- TRAILab/ST-SLidR, community (archive-listed): harvested for another paper, listed under the repository
- Westlake-AI/openmixup, community (archive-listed): harvested for 4 other papers, listed under the repository
- facebookresearch/vissl, community (archive-listed): harvested for 4 other papers, listed under the repository
- hsfzxjy/swavx, community (archive-listed): harvested for 2 other papers, listed under the repository
- sayakpaul/PAWS-TF, community (archive-listed): harvested for another paper, listed under the repository
- vturrisi/solo-learn, community (archive-listed): harvested for 3 other papers, listed under the repository
- PaddlePaddle/PASSL, community (archive-listed): harvested for another paper, listed under the repository
- alibaba/EasyCV, community (archive-listed): harvested for 4 other papers, listed under the repository
- open-mmlab/mmdetection, community (archive-listed): harvested for another paper, listed under the repository
- NVIDIA/apex, found in paper text by Syntology: Syntology's graph links these samples to BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing (arXiv:2206.15076; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
18 repositories listed; official and paper-mentioned ones first.
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
17 samples harvested: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 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.
Licence: 6 of the 17 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
9409540d35684afe · report
fixture: signature x:EagerTensor/4/float, s:float/0/float · returned EagerTensor · level recorded 2026-09-22 c0f578da1f63b8dc · report
fixture: signature image:EagerTensor/4/float, kernel_size:int/0/int, padding:str/0/str · returned EagerTensor · level recorded 2026-09-22 d10fcd33136b539d · report
fixture: signature dataset:_TensorSliceDataset/0/?, size_crops:list/1/int, num_crops:list/1/int, min_scale:list/1/float, max_scale:list/1/float, options:NoneType/0/? · returned tuple · level recorded 2026-09-22 f63e696498472c1e · report
fixture: signature func:callable/0/?, x:EagerTensor/2/float, p:float/0/float · returned EagerTensor · level recorded 2026-09-22 9804c7348e6e7ece · report
fixture: signature image:EagerTensor/3/float, min_scale:float/0/float, max_scale:float/0/float, crop_size:int/0/int · returned EagerTensor · level recorded 2026-09-22 aa8570de6f4e85b0 · report
fixture: signature image:EagerTensor/3/int · returned EagerTensor · level recorded 2026-09-22 f87ad47efb0bcc47 · report
fixture: signature image:dict/0/?, min_scale:float/0/float, max_scale:float/0/float, crop_size:int/0/int · returned EagerTensor · level recorded 2026-09-22 1f7646e4cd1d0e9e · report
451594dfca49b64d · report
d66b0649e0c37be9 · report
fixture: returned ImageFeatureExtractor · level recorded 2026-09-22 ef7fd0fad6c1ce99 · report
fixture: returned SwAVFeatureExtractor · level recorded 2026-09-22 ba4892e53d17ff07 · report
fixture: returned TransformedIndexDataset · level recorded 2026-09-22 65ea068099ec8a00 · report
fixture: returned CL2LLoss · level recorded 2026-09-22 99efca6b93eccdc4 · report
fixture: signature tensors:list/1/Tensor · returned list · level recorded 2026-09-22 census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 lightly/loss/swav_loss.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) ·
58db645a1b52ab84 · report
fixture: signature out:Tensor/2/float, iterations:int/0/int, epsilon:float/0/float, gather_distributed:bool/0/bool · returned Tensor · level recorded 2026-09-22 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
4 assemblies on this paper: 4 harvested, 0 generated, listed in 2 groups (siblings lifted in one batch form one group).
3 sibling assemblies for SwAV (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for SwAV (graph method: SwAV). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 3 siblings
- SwAVFeatureExtractor entry · level 1 · ran ·
ef7fd0fad6c1ce99 - ImageFeatureExtractor helper · level 1 · ran ·
d66b0649e0c37be9 - TransformedIndexDataset helper · level 1 · ran ·
ba4892e53d17ff07
harvested Assembly for SwAV (graph method: SwAV). 6 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- SwALIPLoss entry · level 0 · unverified ·
9b6d7a79e463251f - CL2LLoss helper · level 1 · ran ·
65ea068099ec8a00 - all_gather_batch helper · level 1 · ran · our draft was wrong ·
99efca6b93eccdc4 - get_rank helper · level 1 · ran ·
41ff89724cf234e1 - get_world_size helper · level 1 · ran ·
c9d133b7656f2129 - is_dist_avail_and_initialized helper · level 1 · ran ·
5f205488cb7b9004
harvested Assembly for SwAV (graph method: SwAV). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- SwaVLoss entry · level 0 · unverified ·
03392c922af8bf4c - sinkhorn helper · level 1 · ran; the contract check could not run (RAISES) ·
58db645a1b52ab84
harvested Assembly for multi-crop (graph method: multi-crop). 9 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
- get_multires_dataset entry · level 1 · ran · our draft was wrong ·
d10fcd33136b539d - tie_together helper · level 1 · ran · honoured contract ·
f87ad47efb0bcc47 - custom_augment data_transform · level 0 · unverified ·
451594dfca49b64d - random_resize_crop data_transform · level 1 · ran; the contract check could not run (RAISES) ·
9804c7348e6e7ece - scale_image data_transform · level 1 · ran · violated contract ·
aa8570de6f4e85b0 - color_drop helper · level 0 · unverified ·
1f7646e4cd1d0e9e - color_jitter helper · level 1 · ran; the contract check could not run (RAISES) ·
9409540d35684afe - gaussian_blur helper · level 1 · ran; the contract check could not run (RAISES) ·
c0f578da1f63b8dc - random_apply helper · level 1 · ran · our draft was wrong ·
f63e696498472c1e
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="2006.09882") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
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
Introduced by this paper: SwAV
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