Papers › Unsupervised Hashing with Contrastive Information Bottleneck

Unsupervised Hashing with Contrastive Information Bottleneck

13 May 2021arXiv:2105.06138archive 2025-07-28

Zexuan Qiu, Qinliang Su, Zijing Ou, Jianxing Yu, Changyou Chen

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines.

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.

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

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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.

qiuzx2/CIBHash officialmentioned in paperpytorchSyntology: 15 samples, 11 ran (3 instrument-failed) · 4 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

15 samples harvested: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 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 · violated contract
3ran · our draft was wrong
7ran
4unverified

Licence: 0 of the 15 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 qiuzx2/CIBHash. “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.

qiuzx2/CIBHash official repository 15 samples, 11 ran (3 instrument-failed) · 4 unverified
GaussianBlur in 9 papers model/CIBHash.py ran MIT (permissive) · 545219e390d7b28b · report fixture: returned GaussianBlur · level recorded 2026-09-22
Logger in 25 papers model/CIBHash.py ran MIT (permissive) · a5f55809f0ced9ca · report fixture: returned Logger · level recorded 2026-09-22
MyTestDataset model/CIBHash.py ran MIT (permissive) · a28c9c0199cb6d53 · report fixture: returned MyTestDataset · level recorded 2026-09-22
MyTrainDataset model/CIBHash.py ran MIT (permissive) · de641f731f9c0c61 · report fixture: returned MyTrainDataset · level recorded 2026-09-22
NtXentLoss model/CIBHash.py ran · metamorphic tier: deterministic MIT (permissive) · b2b75636ac168c2e · report fixture: returned NtXentLoss · level recorded 2026-09-22
calculate_hamming model/CIBHash.py ran · violated contract fingerprinted MIT (permissive) · 60f0a788af0cca27 · report fixture: signature B1:ndarray/1/float, B2:ndarray/2/float · returned ndarray · level recorded 2026-09-22
calculate_top_map model/CIBHash.py ran · our draft was wrong fingerprinted MIT (permissive) · 2713054f03946cac · report fixture: signature qB:ndarray/2/float, rB:ndarray/2/float, queryL:ndarray/2/float, retrievalL:ndarray/2/float, topk:int/0/int · returned float64 · level recorded 2026-09-22
compress in 35 papers
census: 1 implementation from 5 papers, 1 distinct output on one shared input
model/CIBHash.py ran · our draft was wrong MIT (permissive) · 9d8f8e1077379f49 · report fixture: signature train:list/1/tuple, test:list/1/tuple, encode_discrete:callable/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
get_cifar in 5 papers model/CIBHash.py ran MIT (permissive) · dd5e14fd69dff667 · report fixture: returned tuple · level recorded 2026-09-22
hash in 6 papers model/CIBHash.py ran MIT (permissive) · 446c9e1a244aca95 · report fixture: returned hash · level recorded 2026-09-22
hash_layer model/CIBHash.py ran · our draft was wrong fingerprinted MIT (permissive) · 6dfd48e834be71b6 · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Base_Model model/CIBHash.py unverified MIT (permissive) · 7eebc68d4cc2574e · report
CIBHash model/CIBHash.py unverified MIT (permissive) · b95d18b296ff8c21 · report
Data in 7 papers model/CIBHash.py unverified MIT (permissive) · 6ae75be554ee6746 · report
LabeledData model/CIBHash.py unverified MIT (permissive) · 04adc0d5624cd788 · 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 Unsupervised Hashing with Contrastive Information Bottleneck (graph method: Unsupervised Hashing with Contrastive Information Bottleneck). 15 bricks; individually on a fixture: 11 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. CIBHash entry · level 0 · unverified · b95d18b296ff8c21
  2. Base_Model helper · level 0 · unverified · 7eebc68d4cc2574e
  3. NtXentLoss loss · level 1 · ran · b2b75636ac168c2e
  4. hash_layer helper · level 1 · ran · our draft was wrong · 6dfd48e834be71b6
  5. LabeledData helper · level 0 · unverified · 04adc0d5624cd788
  6. Logger helper · level 1 · ran · a5f55809f0ced9ca
  7. calculate_hamming helper · level 1 · ran · violated contract · 60f0a788af0cca27
  8. calculate_top_map helper · level 1 · ran · our draft was wrong · 2713054f03946cac
  9. compress helper · level 1 · ran · our draft was wrong · 9d8f8e1077379f49
  10. hash helper · level 1 · ran · 446c9e1a244aca95
  11. Data helper · level 0 · unverified · 6ae75be554ee6746
  12. get_cifar helper · level 1 · ran · dd5e14fd69dff667
  13. GaussianBlur helper · level 1 · ran · 545219e390d7b28b
  14. MyTestDataset helper · level 1 · ran · a28c9c0199cb6d53
  15. MyTrainDataset helper · level 1 · ran · de641f731f9c0c61

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="2105.06138") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

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