Papers › Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to...

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

30 Oct 2022arXiv:2210.16834archive 2025-07-28

Jing Xu, Xu Luo, Xinglin Pan, Wenjie Pei, Yanan Li, Zenglin Xu

Few-shot learning (FSL) targets at generalization of vision models towards unseen tasks without sufficient annotations. Despite the emergence of a number of few-shot learning methods, the sample selection bias problem, i.e., the sensitivity to the limited amount of support data, has not been well understood. In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task. This motivates us to propose an extremely simple feature transformation to alleviate this problem, dubbed Task Centroid Projection Removing (TCPR). TCPR is applied directly to all image features in a given task, aiming at removing the dimension of features along the direction of the task centroid. While the exact task centroid cannot be accurately obtained from limited data, we estimate it using base features that are each similar to one of the support features. Our method effectively prevents features from being too close to the task centroid. Extensive experiments over ten datasets from different domains show that TCPR can reliably improve classification accuracy across various feature extractors, training algorithms and datasets. The code has been made available at https://github.com/KikimorMay/FSL-TCBR.

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 12 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 3 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: official repository: 6 samples from 1 repository, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 6 ran (6 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 12 samples that ran have no recorded date.

kikimormay/fsl-tcbr officialmentioned in paperpytorchSyntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
uitml/nohub mentioned on GitHubpytorchMITSyntology: 6 samples, 6 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

12 samples harvested: 12 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 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
3ran · our draft was wrong
1ran; the contract check could not run
7ran

Licence: 6 of the 12 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 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.

kikimormay/fsl-tcbr official repository 6 samples, 6 ran (4 instrument-failed) · 0 unverified
L2SquareDist models/proo_head.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9148b4837084aa06 · report fixture: signature A:Tensor/3/float, B:Tensor/3/float, base_means:Tensor/1/float, average:bool/0/bool · returned Tensor · level recorded 2026-09-22
PN_head models/proo_head.py ran no licence file found · pointer only · a878f89801621e70 · report fixture: returned PN_head · level recorded 2026-09-22
box_cox evaluate_DC_minusEffect.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 40fb33e3f0e18042 · report fixture: signature data:ndarray/2/float, beta:float/0/float · returned ndarray · level recorded, date not recorded
gen_clusters gaussian_simulation.py ran · honoured contract fingerprinted no licence file found · pointer only · 38490fabee69591b · report fixture: signature a:float/0/float, sample_num:int/0/int · returned tuple · level recorded, date not recorded
get_cos_sin evaluate_DC_minusEffect.py ran · our draft was wrong fingerprinted no licence file found · pointer only · d545754a366e78e9 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned tuple · level recorded, date not recorded
mean_confidence_interval in 16 papers evaluate_DC_minusEffect.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 02885b711bbe655c · report fixture: signature data:list/1/float, confidence:float/0/float · returned tuple · level recorded, date not recorded
uitml/nohub community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
compute_classification_metrics src/evaluate.py ran MIT (permissive) · ef7087bcf8b23f9c · report fixture: signature query_labels:Tensor/2/int, query_predictions:Tensor/2/int · returned dict · level recorded 2026-09-25
dict_means src/helpers.py ran fingerprinted MIT (permissive) · a1d8a3e0deeaaf5c · report fixture: signature dicts:list/1/dict · returned dict · level recorded 2026-09-25
get_pca_weights src/pca.py ran fingerprinted MIT (permissive) · 8d0ff3ac7756bd95 · report fixture: signature inputs:Tensor/3/float · returned Tensor · level recorded 2026-09-25
initial_weights src/classifiers/simpleshot.py ran MIT (permissive) · f9f219e499515fa0 · report fixture: signature support_features:Tensor/3/float, support_labels:Tensor/2/int, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-25
npy src/helpers.py ran MIT (permissive) · 968801ffa2d3b187 · report fixture: signature t:Tensor/2/float, to_cpu:bool/0/bool · returned ndarray · level recorded 2026-09-25
transpose_list_dict src/helpers.py ran MIT (permissive) · c84ca57bf718dc2e · report fixture: signature dicts:list/1/dict · returned dict · level recorded 2026-09-25

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 Task Centroid Projection Removing (TCPR) (graph method: Task Centroid Projection Removing (TCPR)). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. PN_head entry · level 1 · ran · a878f89801621e70
  2. L2SquareDist helper · level 1 · ran · our draft was wrong · 9148b4837084aa06

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="2210.16834") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Few-Shot LearningSelection bias

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

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