Papers › Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Zhirong Wu, Yuanjun Xiong, Stella Yu, Dahua Lin
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional domain of supervised learning: Can we learn a good feature representation that captures apparent similarity among instances, instead of classes, by merely asking the feature to be discriminative of individual instances? We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes. Our experimental results demonstrate that, under unsupervised learning settings, our method surpasses the state-of-the-art on ImageNet classification by a large margin. Our method is also remarkable for consistently improving test performance with more training data and better network architectures. By fine-tuning the learned feature, we further obtain competitive results for semi-supervised learning and object detection tasks. Our non-parametric model is highly compact: With 128 features per image, our method requires only 600MB storage for a million images, enabling fast nearest neighbour retrieval at the run time.
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="1805.01978")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1805.01978", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1805.01978")
Code
The archive's official repository (zhirongw/lemniscate.pytorch) was not harvested; the 23 samples below come from 9 community repositories.
Syntology 23 code samples harvested from 9 repositories linked to this paper: 19 ran (of which 14 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 23 samples from 9 repositories, 19 ran (17 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 2 of its repositories that Syntology harvested for other papers:
- HobbitLong/CMC, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/vissl, community (archive-listed): harvested for 4 other papers, listed under the repository
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.
15 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
23 samples harvested: 19 ran (of which 14 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 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: 16 of the 23 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 9 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.
3890fd0692fdd19f · report
fixture: signature N:int/0/int · returned Tensor · level recorded 2026-09-22 c4e32d2f2f124965 · report
fixture: signature gpu_id:str/0/str · returned device · level recorded 2026-09-22 893c648e49a82a33 · report
ce0d9e87d7214f2a · report
b1f0c5d369793e61 · report
fixture: returned NCEAverage · level recorded 2026-09-22 711a1797529b0c79 · report
fixture: returned NCEFunction · level recorded 2026-09-22 8d07fbd55802678f · report
fixture: returned ActivationAndGradients · level recorded 2026-09-22 d466f84425f5b627 · report
fixture: returned ClassifierOutputTarget · level recorded 2026-09-22 521ff999fdd4b08e · report
fixture: returned DynamicAccumulatedAttentionMap · level recorded 2026-09-22 c8d2726addbf44f6 · report
fixture: signature tensor:Tensor/3/float, height:int/0/int, width:int/0/int · returned Tensor · level recorded 2026-09-22 40d8de9bf103b33f · report
fixture: returned BatchCriterion · level recorded 2026-09-22 cc7f025d23fca482 · report
fixture: signature N:int/0/int · returned Tensor · level recorded 2026-09-22 8b28108d8cd9cedf · report
fixture: signature x:Tensor/2/float, y:Tensor/1/int · returned Tensor · level recorded 2026-09-24 732448859bf05210 · report
fixture: returned NCEAverage · level recorded 2026-09-22 af9f28352bd7e0df · report
fixture: returned NCEFunction · level recorded 2026-09-22 f880630982d445cc · report
fixture: returned AliasMethod · level recorded 2026-09-22 e9b6afbeea8c2280 · report
fixture: returned NCEAverage · level recorded 2026-09-22 6de2a2fbb24c09f4 · report
77cfd89674b8f37b · report
fixture: returned NCEAverage · level recorded 2026-09-22 c466639ec9235e60 · report
fixture: returned NCEFunction · level recorded 2026-09-22 7f8ed4a41b193cc7 · report
fixture: returned AliasMethod · level recorded 2026-09-22 28d82e0982d698f7 · report
fixture: returned MemoryInsDis · 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.
9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
9 sibling assemblies for Non-Parametric Instance Discrimination (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 4 bricks; individually on a fixture: 4 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 9 siblings
- DynamicAccumulatedAttentionMap entry · level 1 · ran ·
521ff999fdd4b08e - ActivationAndGradients helper · level 1 · ran ·
8d07fbd55802678f - ClassifierOutputTarget helper · level 1 · ran ·
d466f84425f5b627 - reshape_transformation helper · level 1 · ran; the contract check could not run (RAISES) ·
c8d2726addbf44f6
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 3 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) · 1 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 9 siblings
- NCEAverage entry · level 1 · ran ·
e9b6afbeea8c2280 - AliasMethod helper · level 1 · ran ·
f880630982d445cc - NCEFunction loss · level 0 · unverified ·
6de2a2fbb24c09f4
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 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 9 siblings
- NCEAverage entry · level 1 · ran ·
732448859bf05210 - AliasMethod sampler · level 1 · ran ·
f880630982d445cc - NCEFunction model · level 1 · ran ·
af9f28352bd7e0df
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 9 siblings
- BatchCriterion entry · level 1 · ran ·
40d8de9bf103b33f
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 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 9 siblings
- MemoryInsDis entry · level 1 · ran ·
28d82e0982d698f7 - AliasMethod helper · level 1 · ran ·
7f8ed4a41b193cc7
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 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 9 siblings
- NCEAverage entry · level 1 · ran ·
b1f0c5d369793e61 - AliasMethod sampler · level 1 · ran ·
f880630982d445cc - NCEFunction helper · level 1 · ran ·
711a1797529b0c79
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 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 9 siblings
- NCEAverage entry · level 1 · ran ·
77cfd89674b8f37b - AliasMethod helper · level 1 · ran ·
f880630982d445cc - NCEFunction loss · level 1 · ran ·
c466639ec9235e60
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 3 bricks; individually on a fixture: 2 ran (of which 0 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) · 1 unverified. The assembly has not been run end-to-end.
one of 9 siblings
- NCEAverage entry · level 1 · ran ·
8b28108d8cd9cedf - AliasMethod helper · level 1 · ran ·
cc7f025d23fca482 - NCEFunction loss · level 0 · unverified ·
12c846f2b380b4c7
harvested Assembly for Non-Parametric Instance Discrimination (graph method: Non-Parametric Instance Discrimination). 4 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 9 siblings
- NCEAverage entry · level 0 · unverified ·
893c648e49a82a33 - AliasMethod sampler · level 1 · ran ·
3890fd0692fdd19f - NCEFunction update_rule · level 0 · unverified ·
ce0d9e87d7214f2a - get_device helper · level 1 · ran · our draft was wrong ·
c4e32d2f2f124965
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="1805.01978") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Contrastive Learning | imagenet-1k | ResNet50 | ImageNet Top-1 Accuracy | 56.5 | #13 of 14 | Archive leaderboard | report |
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
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