Papers › HashNet: Deep Learning to Hash by Continuation

HashNet: Deep Learning to Hash by Continuation

2 Feb 2017ICCV 2017 10arXiv:1702.00758archive 2025-07-28

Zhangjie Cao, Mingsheng Long, Jian-Min Wang, Philip S. Yu

Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the ill-posed gradient difficulty in the optimization with sign activations, existing deep learning to hash methods need to first learn continuous representations and then generate binary hash codes in a separated binarization step, which suffer from substantial loss of retrieval quality. This work presents HashNet, a novel deep architecture for deep learning to hash by continuation method with convergence guarantees, which learns exactly binary hash codes from imbalanced similarity data. The key idea is to attack the ill-posed gradient problem in optimizing deep networks with non-smooth binary activations by continuation method, in which we begin from learning an easier network with smoothed activation function and let it evolve during the training, until it eventually goes back to being the original, difficult to optimize, deep network with the sign activation function. Comprehensive empirical evidence shows that HashNet can generate exactly binary hash codes and yield state-of-the-art multimedia retrieval performance on standard benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

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 16 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (8 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

thuml/HashNet officialmentioned in paperpytorchMITSyntology: 11 samples, 9 ran (1 instrument-failed) · 2 unverified report
hatimwen/paddle_hashnet paddleApache-2.0Syntology: 5 samples, 5 ran (0 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

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 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
1ran · our draft was wrong
12ran
2unverified

Licence: 2 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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.

thuml/HashNet official repository 11 samples, 9 ran (1 instrument-failed) · 2 unverified
image_test in 9 papers pytorch/src/pre_process.py ran MIT (permissive) · dff451db0315485c · report fixture: signature resize_size:int/0/int, crop_size:int/0/int · returned Compose · level recorded 2026-09-25
image_test_10crop pytorch/src/pre_process.py ran MIT (permissive) · 9a338479bd269e9b · report fixture: signature resize_size:int/0/int, crop_size:int/0/int · returned dict · level recorded 2026-09-25
image_train in 18 papers pytorch/src/pre_process.py ran MIT (permissive) · 3331c5176304df6a · report fixture: signature resize_size:int/0/int, crop_size:int/0/int · returned Compose · level recorded 2026-09-25
inv_lr_scheduler in 11 papers pytorch/src/lr_schedule.py ran · our draft was wrong MIT (permissive) · 3ce1df52d4a961b8 · report fixture: signature param_lr:list/1/float, optimizer:SGD/0/?, iter_num:int/0/int, gamma:float/0/float, power:float/0/float, init_lr:float/0/float · returned SGD · level recorded 2026-09-22
multistep_lr_scheduler pytorch/src/lr_schedule.py ran MIT (permissive) · b0c5a2db3d6ec084 · report fixture: signature param_lr:list/1/float, optimizer:SGD/0/?, init_lr:float/0/float, epoch:int/0/int · returned SGD · level recorded 2026-09-25
pairwise_loss in 6 papers pytorch/src/loss.py ran MIT (permissive) · 1cef1cb746b4c73f · report fixture: signature outputs1:Tensor/2/float, outputs2:Tensor/2/float, label1:Tensor/2/float, label2:Tensor/2/float, sigmoid_param:float/0/float, l_threshold:float/0/float, class_num:float/0/float · returned Tensor · level recorded 2026-09-25
pairwise_loss_updated pytorch/src/loss.py ran MIT (permissive) · 77901aeefce81a76 · report fixture: signature outputs1:Tensor/2/float, outputs2:Tensor/2/float, label1:Tensor/2/int, label2:Tensor/2/int · returned Tensor · level recorded 2026-09-25
pil_loader in 144 papers pytorch/src/data_list.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 1df9a5ffd9b38c34 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22
step_lr_scheduler pytorch/src/lr_schedule.py ran MIT (permissive) · 0dfc49084aa7fa24 · report fixture: signature param_lr:list/1/float, optimizer:SGD/0/?, iter_num:int/0/int, gamma:float/0/float, step:int/0/int, init_lr:float/0/float · returned SGD · level recorded 2026-09-25
accimage_loader in 47 papers pytorch/src/data_list.py unverified MIT (permissive) · 9dcef767571b38d7 · report
make_dataset in 144 papers pytorch/src/data_list.py unverified MIT (permissive) here; the stored copy is pointer only · 2301055cb33836bc · report
hatimwen/paddle_hashnet community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
CalcHammingDist utils/tools.py ran fingerprinted Apache-2.0 (permissive) · fec8bc71986e9775 · report fixture: signature B1:ndarray/2/float, B2:ndarray/2/float · returned ndarray · level recorded 2026-09-25
CalcTopMap utils/tools.py ran Apache-2.0 (permissive) · ac4069aac5bd1718 · report fixture: signature rB:ndarray/2/float, qB:ndarray/2/float, retrievalL:ndarray/2/float, queryL:ndarray/2/float, topk:int/0/int · returned float64 · level recorded 2026-09-26
config_dataset utils/datasets.py ran Apache-2.0 (permissive) · 5a36b6fd1493e872 · report fixture: signature config:Config/0/? · returned Config · level recorded 2026-09-26
get_args in 84 papers deploy/inference_python/infer.py ran Apache-2.0 (permissive) · a66b5598134a7bcd · report fixture: signature add_help:bool/0/bool · returned Namespace · level recorded 2026-09-26
get_logger in 383 papers main_multi_gpu.py ran Apache-2.0 (permissive) · 3d300924bfb82d8f · report fixture: signature filename:str/0/str, logger_name:str/0/str · returned Logger · level recorded 2026-09-26

Tasks

BinarizationDeep LearningRepresentation LearningRetrieval

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