Papers › CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

21 Oct 2021arXiv:2110.11316archive 2025-07-28

Andreas Fürst, Elisabeth Rumetshofer, Johannes Lehner, Viet Tran, Fei Tang, Hubert Ramsauer, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto-Nemling, Sepp Hochreiter

CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a foundation model like BERT or GPT3. CLIP vision models that have a rich representation are pre-trained using the InfoNCE objective and natural language supervision before they are fine-tuned on particular tasks. Though CLIP excels at zero-shot transfer learning, it suffers from an explaining away problem, that is, it focuses on one or few features, while neglecting other relevant features. This problem is caused by insufficiently extracting the covariance structure in the original multi-modal data. We suggest to use modern Hopfield networks to tackle the problem of explaining away. Their retrieved embeddings have an enriched covariance structure derived from co-occurrences of features in the stored embeddings. However, modern Hopfield networks increase the saturation effect of the InfoNCE objective which hampers learning. We propose to use the InfoLOOB objective to mitigate this saturation effect. We introduce the novel "Contrastive Leave One Out Boost" (CLOOB), which uses modern Hopfield networks for covariance enrichment together with the InfoLOOB objective. In experiments we compare CLOOB to CLIP after pre-training on the Conceptual Captions and the YFCC dataset with respect to their zero-shot transfer learning performance on other datasets. CLOOB consistently outperforms CLIP at zero-shot transfer learning across all considered architectures and datasets.

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 11 code samples harvested from 3 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); community: 7 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 7 samples that ran have no recorded date.

ml-jku/cloob officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 4 ran (4 instrument-failed) · 0 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 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.

1ran · honoured contract
6ran · our draft was wrong
4unverified

Licence: 4 of the 11 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”. “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.

ml-jku/cloob official repository 4 samples, 4 ran (4 instrument-failed) · 0 unverified
cloob src/training/methods.py ran · our draft was wrong licence not identified · pointer only · 6dd41de81496f6ba · report fixture: signature image_features:Tensor/2/float, text_features:Tensor/2/float, inv_tau:Tensor/0/float, hopfield_layer:callable/0/? · returned Tensor · level recorded 2026-09-22
hopfield src/training/methods.py ran · our draft was wrong licence not identified · pointer only · e0792a694e05deeb · report fixture: signature state_patterns:Tensor/2/float, stored_patterns:Tensor/2/float, hopfield_layer:callable/0/? · returned Tensor · level recorded 2026-09-22
hopfield_retrieval src/training/methods.py ran · our draft was wrong licence not identified · pointer only · 4d5e096e98580645 · report fixture: signature image_features:Tensor/2/float, text_features:Tensor/2/float, hopfield_layer:callable/0/? · returned tuple · level recorded 2026-09-22
infoLOOB_loss src/training/methods.py ran · our draft was wrong fingerprinted licence not identified · pointer only · f14e4cd457038dcb · report fixture: signature x:Tensor/2/float, y:Tensor/2/float, i:Tensor/2/bool, inv_tau:Tensor/0/float · returned Tensor · level recorded 2026-09-22
JD-P/cloob-latent-diffusion community 3 samples, 3 ran (2 instrument-failed) · 0 unverified
eval_mode train_latent_diffusion.py ran · our draft was wrong MIT (permissive) · 1d4710b26e6ea9f5 · report fixture: signature model:callable/0/? · returned _GeneratorContextManager · level recorded, date not recorded
get_alphas_sigmas train_latent_diffusion.py ran · honoured contract fingerprinted MIT (permissive) · 7543087fb92417f3 · report fixture: signature t:Tensor/0/float · returned tuple · level recorded, date not recorded
parse_prompt in 9 papers cfg_sample.py ran · our draft was wrong fingerprinted MIT (permissive) · 1fdcc5450a1266f3 · report fixture: signature prompt:str/0/str, default_weight:float/0/float · returned tuple · level recorded, date not recorded
crowsonkb/cloob-training community 4 samples, 0 ran · 4 unverified
download_checkpoint cloob_training/pretrained.py unverified MIT (permissive) · 07006f9eb4731a60 · report
get_and_init_model cloob_training/model.py unverified MIT (permissive) · 1b433f466bd550fe · report
get_config in 203 papers cloob_training/pretrained.py unverified MIT (permissive) · 704cbcc71dd35d3d · report
get_hk_model cloob_training/model.py unverified MIT (permissive) · 1e3e01f4209f0a95 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for CLOOB (graph method: CLOOB). 4 bricks; individually on a fixture: 4 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; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. cloob entry · level 1 · ran · our draft was wrong · 6dd41de81496f6ba
  2. hopfield_retrieval model · level 1 · ran · our draft was wrong · 4d5e096e98580645
  3. infoLOOB_loss loss · level 1 · ran · our draft was wrong · f14e4cd457038dcb
  4. hopfield helper · level 1 · ran · our draft was wrong · e0792a694e05deeb

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="2110.11316") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTCLIPDense ConnectionsDropoutInfoNCELayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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