Papers › Transductive Information Maximization For Few-Shot Learning

Transductive Information Maximization For Few-Shot Learning

25 Aug 2020arXiv:2008.11297archive 2025-07-28

Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony, José Dolz, Pablo Piantanida, Ismail Ben Ayed

We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set. Furthermore, we propose a new alternating-direction solver for our mutual-information loss, which substantially speeds up transductive-inference convergence over gradient-based optimization, while yielding similar accuracy. TIM inference is modular: it can be used on top of any base-training feature extractor. Following standard transductive few-shot settings, our comprehensive experiments demonstrate that TIM outperforms state-of-the-art methods significantly across various datasets and networks, while used on top of a fixed feature extractor trained with simple cross-entropy on the base classes, without resorting to complex meta-learning schemes. It consistently brings between 2% and 5% improvement in accuracy over the best performing method, not only on all the well-established few-shot benchmarks but also on more challenging scenarios,with domain shifts and larger numbers of classes.

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 10 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mboudiaf/TIM officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (1 instrument-failed) · 1 unverified report
sicara/easy-few-shot-learning pytorchSyntology: 3 samples, 3 ran (1 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

10 samples harvested: 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

2ran · our draft was wrong
7ran
1unverified

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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. 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.

mboudiaf/TIM official repository 7 samples, 6 ran (1 instrument-failed) · 1 unverified
conv_block in 95 papers src/models/Conv4.py ran MIT (permissive) · 02652b1ac1a54dda · report fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-25
get_features in 57 papers src/utils.py ran MIT (permissive) · 12cbd4d101797d30 · report fixture: signature model:callable/0/?, samples:Tensor/2/float · returned Tensor · level recorded 2026-09-25
get_metric in 19 papers src/models/ProtoNet.py ran MIT (permissive) · 235da783eeb0573f · report fixture: signature metric_type:str/0/str · returned function · level recorded 2026-09-25
get_one_hot in 20 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
src/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · a03c85ae21c3b667 · report fixture: signature y_s:Tensor/1/int · returned Tensor · level recorded 2026-09-22
with_augment src/datasets/transform.py ran MIT (permissive) · 97533e04cdf4da7e · report fixture: signature size:int/0/int, disable_random_resize:bool/0/bool, jitter:bool/0/bool · returned Compose · level recorded 2026-09-25
without_augment src/datasets/transform.py ran MIT (permissive) · e1f7a44f9ac823d7 · report fixture: signature size:int/0/int, enlarge:bool/0/bool · returned Compose · level recorded 2026-09-25
get_logs_path src/utils.py unverified MIT (permissive) · e232226ad7c9556f · report
sicara/easy-few-shot-learning community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
FewShotClassifier easyfsl/methods/tim.py ran MIT (permissive) · 637e871cf76bfc10 · report fixture: returned FewShotClassifier · level recorded 2026-09-22
TIM easyfsl/methods/tim.py ran MIT (permissive) · c46ba9a1cacbe109 · report fixture: returned TIM · level recorded 2026-09-22
compute_prototypes in 7 papers easyfsl/methods/tim.py ran · our draft was wrong fingerprinted MIT (permissive) · 31e41d7e676cb492 · report fixture: signature support_features:Tensor/2/float, support_labels:Tensor/1/int · returned Tensor · 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.

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

harvested Assembly for Transductive Information Maximization (TIM) (graph method: Transductive Information Maximization (TIM)). 3 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. TIM entry · level 1 · ran · c46ba9a1cacbe109
  2. FewShotClassifier helper · level 1 · ran · 637e871cf76bfc10
  3. compute_prototypes helper · level 1 · ran · our draft was wrong · 31e41d7e676cb492

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="2008.11297") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Few-Shot Image ClassificationFew-Shot LearningMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CUB 200 5-way 1-shot TIM-GD Accuracy 82.2% #17 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot TIM-GD Accuracy 90.8 #19 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet to CUB - 5 shot learning TIM-GD Accuracy 71 #1 of 2 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) TIM-GD Accuracy 56.1 #3 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) TIM-GD Accuracy 72.8 #3 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) TIM-GD Accuracy 39.3 #1 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) TIM-GD Accuracy 59.5 #1 of 6 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) TIM-GD Accuracy 77.80 #18 of 105 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) TIM-GD Accuracy 82.1 #9 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) TIM-GD Accuracy 89.8 #8 of 51 Archive leaderboard report
Few-Shot Learning Mini-ImageNet - 5-Shot Learning TIM-GD Accuracy 87.4% #2 of 3 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.

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