Papers › Prototype Completion with Primitive Knowledge for Few-Shot Learning

Prototype Completion with Primitive Knowledge for Few-Shot Learning

10 Sep 2020CVPR 2021 1arXiv:2009.04960archive 2025-07-28

Baoquan Zhang, Xutao Li, Yunming Ye, Zhichao Huang, Lisai Zhang

Few-shot learning is a challenging task, which aims to learn a classifier for novel classes with few examples. Pre-training based meta-learning methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. However, results show that the fine-tuning step makes very marginal improvements. In this paper, 1) we figure out the key reason, i.e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning the feature extractor is less meaningful; 2) instead of fine-tuning the feature extractor, we focus on estimating more representative prototypes during meta-learning. Consequently, we propose a novel prototype completion based meta-learning framework. This framework first introduces primitive knowledge (i.e., class-level part or attribute annotations) and extracts representative attribute features as priors. Then, we design a prototype completion network to learn to complete prototypes with these priors. To avoid the prototype completion error caused by primitive knowledge noises or class differences, we further develop a Gaussian based prototype fusion strategy that combines the mean-based and completed prototypes by exploiting the unlabeled samples. Extensive experiments show that our method: (i) can obtain more accurate prototypes; (ii) outperforms state-of-the-art techniques by 2% - 9% in terms of classification accuracy. Our code is available online.

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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 12 ran (8 with no instrument failure; 4 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

zhangbq-research/Prototype_Completion_for_FSL officialmentioned in paperpytorchMITSyntology: 13 samples, 12 ran (4 instrument-failed) · 1 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

13 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
8ran
1unverified

Licence: 0 of the 13 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 zhangbq-research/Prototype_Completion_for_FSL. “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.

zhangbq-research/Prototype_Completion_for_FSL official repository 13 samples, 12 ran (4 instrument-failed) · 1 unverified
CosineNetHead models/classification_heads.py ran MIT (permissive) · 068a0a6a30e1e25c · report fixture: signature k_all:Tensor/2/float, meta_part_infer:callable/0/?, query:Tensor/3/float, support:Tensor/3/float, support_labels:Tensor/2/int, n_way:int/0/int, n_shot:int/0/int, is_scale:bool/0/bool, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-25
CosineNetHead models/classification_heads_orgin.py ran MIT (permissive) · 4ec52ee88c7bc858 · report fixture: signature query:Tensor/3/float, support:Tensor/3/float, support_labels:Tensor/2/int, n_way:int/0/int, n_shot:int/0/int, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-25
FuseCosineNetHead models/classification_heads.py ran MIT (permissive) · f7312cd2956a3b29 · report fixture: signature k_all:Tensor/2/float, meta_part_infer:callable/0/?, query:Tensor/3/float, support:Tensor/3/float, support_labels:Tensor/2/int, n_way:int/0/int, n_shot:int/0/int, is_scale:bool/0/bool, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-25
constructedges prior/make_miniimagenet_primitive_knowledge.py ran MIT (permissive) · 161f62eb1a752b4c · report fixture: signature s:dict/0/?, syns2id:dict/0/? · returned list · level recorded 2026-09-25
conv1x1 in 691 papers models/resnet12_2.py ran MIT (permissive) · de92832114f71d8c · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Conv2d · level recorded 2026-09-24
conv3x3 in 1,376 papers models/resnet12_2.py ran · our draft was wrong MIT (permissive) · e5b7c79b0b62af96 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Conv2d · level recorded 2026-09-24
count_accuracy in 12 papers utils.py ran · our draft was wrong fingerprinted MIT (permissive) · fb61241b42c06d73 · report fixture: signature logits:Tensor/2/float, label:Tensor/1/int · returned Tensor · level recorded 2026-09-26
getwnid prior/make_miniimagenet_primitive_knowledge.py ran MIT (permissive) · 212f1ff29913b717 · report fixture: signature u:MockWordNetObject/0/? · returned str · level recorded 2026-09-25
l2_loss in 136 papers utils.py ran fingerprinted MIT (permissive) · 78ac9e19f328f531 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-25
norm_layer in 17 papers models/resnet12_2.py ran · our draft was wrong MIT (permissive) · f36ac42575cd46ee · report fixture: signature planes:int/0/int · returned BatchNorm2d · level recorded 2026-09-24
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 2 of 6, arg 1: rank 2, kind int, dtype int64
models/classification_heads.py ran · our draft was wrong MIT (permissive) · 7c64c35be7f02395 · report fixture: returned Tensor · level recorded, date not recorded
pick_vectors utils.py ran MIT (permissive) · a2b31023f6121fdf · report fixture: signature dic:dict/0/?, wnids:list/1/str, is_tensor:bool/0/bool · returned Tensor · level recorded 2026-09-25
getnode prior/make_miniimagenet_primitive_knowledge.py unverified MIT (permissive) · 0c7425262620b51b · report

Tasks

AttributeFew-Shot LearningMeta-Learning

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