Papers › Generative Latent Implicit Conditional Optimization when Learning from Small Sample

Generative Latent Implicit Conditional Optimization when Learning from Small Sample

31 Mar 2020arXiv:2003.14297archive 2025-07-28

Idan Azuri, Daphna Weinshall

We revisit the long-standing problem of learning from a small sample, to which end we propose a novel method called GLICO (Generative Latent Implicit Conditional Optimization). GLICO learns a mapping from the training examples to a latent space and a generator that generates images from vectors in the latent space. Unlike most recent works, which rely on access to large amounts of unlabeled data, GLICO does not require access to any additional data other than the small set of labeled points. In fact, GLICO learns to synthesize completely new samples for every class using as little as 5 or 10 examples per class, with as few as 10 such classes without imposing any prior. GLICO is then used to augment the small training set while training a classifier on the small sample. To this end, our proposed method samples the learned latent space using spherical interpolation, and generates new examples using the trained generator. Empirical results show that the new sampled set is diverse enough, leading to improvement in image classification in comparison with the state of the art, when trained on small samples obtained from CIFAR-10, CIFAR-100, and CUB-200.

PaperPDFCodeCode 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 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 10 ran (10 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

IdanAzuri/glico-learning-small-sample officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 10 ran (0 instrument-failed) · 6 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: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 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.

10ran
6unverified

Licence: 0 of the 16 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 IdanAzuri/glico-learning-small-sample. “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. 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.

IdanAzuri/glico-learning-small-sample official repository 16 samples, 10 ran (0 instrument-failed) · 6 unverified
fewshot_setting glico_model/evaluation.py ran fingerprinted MIT (permissive) · a86a74fe9070c8ff · report fixture: signature samples_per_class:int/0/int, im_size:int/0/int · returned int · level recorded 2026-09-25
has_file_allowed_extension in 38 papers glico_model/imagent_folder_loader.py ran MIT (permissive) · 46a47194a5a214b5 · report fixture: signature filename:str/0/str, extensions:tuple/1/str · returned bool · level recorded 2026-09-25
is_image_file in 157 papers glico_model/imagent_folder_loader.py ran MIT (permissive) · 3ed19559ece460a6 · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-25
lerp_mat glico_model/interpolate.py ran fingerprinted MIT (permissive) · cd853a74f6084460 · report fixture: signature start:Tensor/2/float, end:Tensor/2/float, n_steps:int/0/int · returned Tensor · level recorded 2026-09-25
make_dataset in 144 papers glico_model/imagent_folder_loader.py ran MIT (permissive) · f846a37597cc33b1 · report fixture: signature dir:str/0/str, class_to_idx:dict/0/?, extensions:tuple/1/str, is_valid_file:NoneType/0/?, class_cap:NoneType/0/?, ignore_samples_by_path:dict/0/? · returned list · level recorded 2026-09-25
sample_from_iter glico_model/model.py ran MIT (permissive) · 247e9650fd4374b4 · report fixture: signature iterable:list/1/tuple, k:int/0/int · returned list · level recorded 2026-09-25
slerp in 28 papers
census: 6 implementations from 6 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
glico_model/interpolate.py ran MIT (permissive) · b31461d93847c383 · report fixture: signature val:float/0/float, low:ndarray/1/float, high:ndarray/1/float · returned ndarray · level recorded 2026-09-25
slerp_torch glico_model/interpolate.py ran MIT (permissive) · 1fdd932b4ae04228 · report fixture: signature val:float/0/float, low:Tensor/2/float, high:Tensor/2/float · returned Tensor · level recorded 2026-09-25
train_val_split in 14 papers glico_model/cifar10.py ran MIT (permissive) · a727540bc318bdd2 · report fixture: signature labels:ndarray/1/int, n_labeled_per_class:int/0/int, n_unlabled_per_class:int/0/int · returned tuple · level recorded 2026-09-25
train_val_split in 14 papers glico_model/cifar100.py ran MIT (permissive) · 3fb532813fcf4bb5 · report fixture: signature labels:ndarray/1/int, n_labeled_per_class:int/0/int, n_unlabled_per_class:int/0/int · returned tuple · level recorded 2026-09-25
get_cifar10 in 13 papers glico_model/cifar10.py unverified MIT (permissive) · 492e6a1a39e01db2 · report
get_cifar100 glico_model/cifar100.py unverified MIT (permissive) · 70c82888b308c191 · report
get_code glico_model/brwose_data_and_FID.py unverified MIT (permissive) · 76ecc13d5690af8e · report
normalise in 26 papers glico_model/cifar10.py unverified MIT (permissive) · e6db98c4f0c516df · report
normalise in 26 papers glico_model/cifar100.py unverified MIT (permissive) · f0a379836cfa494d · report

Tasks

Conditional Image GenerationData AugmentationImage ClassificationSmall Data Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Small Data Image Classification CIFAR-10, 250 Labels GLICO Top-1 accuracy % 43 #1 of 1 Archive leaderboard report
Small Data Image Classification CIFAR-10, 500 Labels GLICO Accuracy (%) 56.22 #6 of 6 Archive leaderboard report
Small Data Image Classification CIFAR-100, 1000 Labels GLICO Accuracy 28.55 #3 of 3 Archive leaderboard report
Small Data Image Classification CUB-200-2011, 30 samples per class GLICO Accuracy 77.75 #1 of 4 Archive leaderboard report
Small Data Image Classification CUB-200-2011, 5 samples per class GLICO Accuracy 51.52 #1 of 1 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

Auxiliary ClassifierWideResNet

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