Papers › VICRegL: Self-Supervised Learning of Local Visual Features

VICRegL: Self-Supervised Learning of Local Visual Features

4 Oct 2022arXiv:2210.01571archive 2025-07-28

Adrien Bardes, Jean Ponce, Yann Lecun

Most recent self-supervised methods for learning image representations focus on either producing a global feature with invariance properties, or producing a set of local features. The former works best for classification tasks while the latter is best for detection and segmentation tasks. This paper explores the fundamental trade-off between learning local and global features. A new method called VICRegL is proposed that learns good global and local features simultaneously, yielding excellent performance on detection and segmentation tasks while maintaining good performance on classification tasks. Concretely, two identical branches of a standard convolutional net architecture are fed two differently distorted versions of the same image. The VICReg criterion is applied to pairs of global feature vectors. Simultaneously, the VICReg criterion is applied to pairs of local feature vectors occurring before the last pooling layer. Two local feature vectors are attracted to each other if their l2-distance is below a threshold or if their relative locations are consistent with a known geometric transformation between the two input images. We demonstrate strong performance on linear classification and segmentation transfer tasks. Code and pretrained models are publicly available at: https://github.com/facebookresearch/VICRegL

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.

Syntology holds a reference implementation of VICRegL, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='VICRegL') (how to connect); the free check have('2210.01571') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples: 19 from 3 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 20: 16 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 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: official repository: 10 samples from 1 repository, 8 ran (0 with no instrument failure; 8 where Syntology's instrument failed); community (archive-listed): 9 samples from 2 repositories, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 16 samples that ran have no recorded date.

facebookresearch/vicregl officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 8 ran (8 instrument-failed) · 2 unverified report
Futurne/vicreg-loss mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: 7 samples, 5 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

20 samples harvested: 16 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 10 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.

2ran · honoured contract
6ran · our draft was wrong
4ran; the contract check could not run
4ran
4unverified

Licence: 13 of the 20 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 3 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. 1 sample is listed last, in a group without a repository. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

facebookresearch/vicregl official repository 10 samples, 8 ran (8 instrument-failed) · 2 unverified
MLP in 375 papers main_vicregl.py ran · our draft was wrong licence not identified · pointer only · 0393d6f458d1bd7e · report fixture: signature mlp:str/0/str, embedding:str/0/str, norm_layer:str/0/str · returned Sequential · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
main_vicregl.py ran; the contract check could not run (RAISES) licence not identified · pointer only · f59a1c321043b890 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-22
batch_all_gather main_vicregl.py ran · our draft was wrong licence not identified · pointer only · e413e4905a6a548b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
batched_index_select in 44 papers main_vicregl.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 1345f4fc63011f70 · report fixture: signature input:Tensor/4/float, dim:int/0/int, index:Tensor/2/int · returned Tensor · level recorded, date not recorded
make_inputs in 7 papers main_vicregl.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 62036ceee17bee5d · report fixture: returned dict · level recorded, date not recorded
neirest_neighbores main_vicregl.py ran · our draft was wrong fingerprinted licence not identified · pointer only · d53b48478f98d717 · report fixture: signature input_maps:Tensor/3/float, candidate_maps:Tensor/3/float, distances:Tensor/3/float, num_matches:int/0/int · returned tuple · level recorded, date not recorded
neirest_neighbores_on_l2 main_vicregl.py ran · our draft was wrong licence not identified · pointer only · 80bfa31403ede22a · report fixture: signature input_maps:Tensor/3/float, candidate_maps:Tensor/3/float, num_matches:int/0/int · returned tuple · level recorded 2026-09-22
neirest_neighbores_on_location main_vicregl.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 8e775945d18d2299 · report fixture: signature input_location:Tensor/3/float, candidate_location:Tensor/3/float, input_maps:Tensor/3/float, candidate_maps:Tensor/3/float, num_matches:int/0/int · returned tuple · level recorded 2026-09-22
VICRegL main_vicregl.py unverified licence not identified · pointer only · bbe9eaa0bec2c145 · report
gather_center main_vicregl.py unverified licence not identified · pointer only · 7fe4deeb043278d7 · report
Futurne/vicreg-loss community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
VICRegLLoss vicreg_loss/vicregl.py ran · metamorphic tier: deterministic no licence file found · pointer only · 813497ec5b533d79 · report fixture: returned VICRegLLoss · level recorded 2026-09-22
VICRegLoss vicreg_loss/vicregl.py ran · metamorphic tier: deterministic no licence file found · pointer only · 43e2587f6349819b · report fixture: returned VICRegLoss · level recorded 2026-09-22
lightly-ai/lightly community (archive-listed) 7 samples, 5 ran (1 instrument-failed) · 2 unverified
GatherLayer in 12 papers lightly/loss/vicregl_loss.py ran MIT (permissive) · ba565bd2bd01c209 · report fixture: returned GatherLayer · level recorded 2026-09-22
VICRegLoss lightly/loss/vicregl_loss.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 90c615a3b586fa8c · report fixture: returned VICRegLoss · level recorded 2026-09-22
covariance_loss in 5 papers lightly/loss/vicregl_loss.py ran · our draft was wrong fingerprinted MIT (permissive) · 15d4e6fc5c5683f1 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
invariance_loss lightly/loss/vicregl_loss.py ran · honoured contract fingerprinted MIT (permissive) · a20e1319851797c7 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22
variance_loss lightly/loss/vicregl_loss.py ran · honoured contract fingerprinted MIT (permissive) · 44598859a9de393b · report fixture: signature x:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
VICRegLLoss lightly/loss/vicregl_loss.py unverified MIT (permissive) · 6fc75c85f0b33a2c · report
gather in 75 papers lightly/loss/vicregl_loss.py unverified MIT (permissive) · f60f882797a1d561 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · b0f936d4d6ae3b8c · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded, date not recorded

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

4 assemblies on this paper: 3 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for VICRegL (graph method: VICRegL), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 6 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. vicreg_loss entry · level 3 · ran · 7fe9bea097de7ede5641760bfea65e63fee50952e0711bec1557b983b10d7bbb

3 sibling assemblies for VICRegL (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for VICRegL (graph method: VICRegL). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. VICRegLLoss entry · level 1 · ran · 813497ec5b533d79
  2. VICRegLoss helper · level 1 · ran · 43e2587f6349819b

harvested Assembly for VICRegL (graph method: VICRegL). 8 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. VICRegLLoss entry · level 0 · unverified · 6fc75c85f0b33a2c
  2. VICRegLoss helper · level 1 · ran · 90c615a3b586fa8c
  3. covariance_loss helper · level 1 · ran · our draft was wrong · 15d4e6fc5c5683f1
  4. gather helper · level 0 · unverified · f60f882797a1d561
  5. invariance_loss helper · level 1 · ran · honoured contract · a20e1319851797c7
  6. variance_loss helper · level 1 · ran · honoured contract · 44598859a9de393b
  7. world_size helper · level 1 · ran · a1d11ea20c97a5b5
  8. GatherLayer helper · level 1 · ran · ba565bd2bd01c209

harvested Assembly for VICRegL (graph method: VICRegL). 11 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. VICRegL entry · level 0 · unverified · bbe9eaa0bec2c145
  2. MLP model · level 1 · ran · our draft was wrong · 0393d6f458d1bd7e
  3. accuracy helper · level 1 · ran; the contract check could not run (RAISES) · f59a1c321043b890
  4. batch_all_gather helper · level 1 · ran · our draft was wrong · e413e4905a6a548b
  5. gather_center helper · level 0 · unverified · 7fe4deeb043278d7
  6. neirest_neighbores_on_l2 loss · level 1 · ran · our draft was wrong · 80bfa31403ede22a
  7. neirest_neighbores_on_location loss · level 1 · ran · our draft was wrong · 8e775945d18d2299
  8. off_diagonal helper · level 1 · ran; the contract check could not run · 3e30d88eaef01190
  9. FullGatherLayer helper · level 1 · ran · 90bc3c3bb8e6523b
  10. neirest_neighbores loss · level 1 · ran · our draft was wrong · d53b48478f98d717
  11. batched_index_select helper · level 1 · ran; the contract check could not run (RAISES) · 1345f4fc63011f70

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="2210.01571") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

SegmentationSelf-Supervised Learning

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