Papers › Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

19 Jan 2023CVPR 2023 1arXiv:2301.08243archive 2025-07-28

Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann Lecun, Nicolas Ballas

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.

PaperPDFConference PDFCodeCode 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 14 code samples harvested from 3 repositories linked to this paper: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 11 samples from 2 repositories, 3 ran (1 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/ijepa officialmentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
gaasher/I-JEPA mentioned on GitHubpytorchMITSyntology: not harvested report
vectorinstitute/mmlearn mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale (arXiv:2405.17537; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
waterdisappear/sar-jepa mentioned on GitHubpytorchSyntology: 10 samples, 3 ran (2 instrument-failed) · 7 unverified report
waterdisappear/sar-kpga mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
lightly-ai/lightly pytorchSyntology: 1 sample, 0 ran · 1 unverified report
gitlab.com/birder/birder pytorchSyntology: not harvested 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

14 samples harvested: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 9 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 · honoured contract
2ran · our draft was wrong
2ran
9unverified

Licence: 13 of the 14 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. “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 1 sample 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/ijepa official repository 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/models/vision_transformer.py ran · metamorphic tier: invariant licence not identified · pointer only · 5a10f46fdda5375c · report fixture: signature x:Tensor/3/float, return_attention:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_2d_sincos_pos_embed in 170 papers src/models/vision_transformer.py ran · honoured contract fingerprinted licence not identified · pointer only · fc939725b0bb127b · report fixture: signature embed_dim:int/0/int, grid_size:int/0/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-22
VisionTransformerPredictor src/models/vision_transformer.py unverified licence not identified · pointer only · 9d96610a96ece7b7 · report
waterdisappear/sar-jepa community (archive-listed) 10 samples, 3 ran (2 instrument-failed) · 7 unverified
GF Pretraining/models_lomar.py ran licence not identified · pointer only · abc90f0c6dffd99f · report fixture: returned GF · level recorded 2026-09-22
get_rpe_config Pretraining/models_lomar.py ran · our draft was wrong licence not identified · pointer only · ab8156d726620d7e · report fixture: signature ratio:float/0/float, method:int/0/int, mode:str/0/str, shared_head:bool/0/bool, skip:int/0/int, rpe_on:str/0/str · returned EasyDict · level recorded 2026-09-22
get_single_rpe_config Pretraining/models_lomar.py ran · our draft was wrong fingerprinted licence not identified · pointer only · b67bfbf8a86f8ae3 · report fixture: signature ratio:float/0/float, method:int/0/int, mode:str/0/str, shared_head:bool/0/bool, skip:int/0/int · returned EasyDict · level recorded 2026-09-22
MaskedAutoencoderViT in 14 papers Pretraining/models_lomar.py unverified licence not identified · pointer only · 91e43c1af69c43ab · report
build_rpe Pretraining/models_lomar.py unverified licence not identified · pointer only · 7f5fc306914d0a48 · report
get_bucket_ids_2d Pretraining/models_lomar.py unverified licence not identified · pointer only · d5148a7973cd80a8 · report
iRPE Pretraining/models_lomar.py unverified licence not identified · pointer only · 0a8854a10b0caba2 · report
iRPE_Cross Pretraining/models_lomar.py unverified licence not identified · pointer only · 6ea577bc7d8c4a62 · report
lightly-ai/lightly community (archive-listed) 1 sample, 0 ran · 1 unverified
IJEPAPredictor lightly/models/modules/ijepa.py unverified MIT (permissive) · 534c33c21ec7b299 · 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. 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Imagebased Joint-Embedding Predictive Architecture (I-JEPA) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Imagebased Joint-Embedding Predictive Architecture (I-JEPA) (graph method: Imagebased Joint-Embedding Predictive Architecture (I-JEPA)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. IJEPAPredictor entry · level 0 · unverified · 534c33c21ec7b299

harvested Assembly for Imagebased Joint-Embedding Predictive Architecture (I-JEPA) (graph method: Imagebased Joint-Embedding Predictive Architecture (I-JEPA)). 25 bricks; individually on a fixture: 15 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; 9 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. MaskedAutoencoderViT entry · level 0 · unverified · 91e43c1af69c43ab
  2. Block model · level 0 · unverified · 6710d315e3285047
  3. GF helper · level 1 · ran · abc90f0c6dffd99f
  4. PatchEmbed model · level 1 · ran · 468a394a75068b28
  5. get_2d_sincos_pos_embed helper · level 0 · unverified · 43ab33710deb02f8
  6. Attention model · level 0 · unverified · d5d4d27df91c3a11
  7. Mlp model · level 1 · ran · a1715055832f71fd
  8. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  9. build_rpe helper · level 0 · unverified · 7f5fc306914d0a48
  10. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c
  11. METHOD helper · level 1 · ran · 6f2776fda8eaa86b
  12. iRPE helper · level 0 · unverified · 0a8854a10b0caba2
  13. iRPE_Cross helper · level 0 · unverified · 6ea577bc7d8c4a62
  14. get_bucket_ids_2d helper · level 0 · unverified · d5148a7973cd80a8
  15. get_bucket_ids_2d_without_skip helper · level 1 · ran · our draft was wrong · ab89b48444865c77
  16. get_absolute_positions helper · level 1 · ran · honoured contract · ba23bbb042430585
  17. get_num_buckets helper · level 1 · ran · honoured contract · 0deaebd0135ec340
  18. _rp_2d_cross_cols helper · level 1 · ran; the contract check could not run · 3c90a55d42ebd29a
  19. _rp_2d_cross_rows helper · level 1 · ran; the contract check could not run · afa68c96506b7ca4
  20. _rp_2d_euclidean helper · level 1 · ran · our draft was wrong · 2afb88f76e6694db
  21. _rp_2d_product helper · level 1 · ran; the contract check could not run · 5e64867591fc57ca
  22. _rp_2d_quant helper · level 1 · ran · our draft was wrong · ea730722397f9780
  23. get_rpe_config helper · level 1 · ran · our draft was wrong · ab8156d726620d7e
  24. get_single_rpe_config helper · level 1 · ran · our draft was wrong · b67bfbf8a86f8ae3
  25. piecewise_index helper · level 1 · ran · our draft was wrong · c69948747b50336f

harvested Assembly for Imagebased Joint-Embedding Predictive Architecture (I-JEPA) (graph method: Imagebased Joint-Embedding Predictive Architecture (I-JEPA)). 13 bricks; individually on a fixture: 10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. VisionTransformerPredictor entry · level 0 · unverified · 9d96610a96ece7b7
  2. Block model · level 1 · ran · 5a10f46fdda5375c
  3. apply_masks helper · level 0 · unverified · 8e6b06075e39c310
  4. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · fc939725b0bb127b
  5. repeat_interleave_batch helper · level 1 · ran · our draft was wrong · f9da1ce7ab746872
  6. trunc_normal_ helper · level 1 · ran · our draft was wrong · 359975e35f7d1d79
  7. Attention model · level 1 · ran · 3806102629027da3
  8. DropPath helper · level 1 · ran · ad5f80b54573c0e0
  9. MLP model · level 1 · ran · 00ab6e2a5e0dd98d
  10. drop_path helper · level 1 · ran; the contract check could not run · 55120f2026b56aa2
  11. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 4fd80de79832745d
  12. _no_grad_trunc_normal_ helper · level 1 · ran · our draft was wrong · 307242ac3279e182
  13. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 4bdd36eab04c3f62

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="2301.08243") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Depth EstimationDepth PredictionObject CountingSelf-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