SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.04390 · 2020

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 7 failures of our instrument; 2 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2003.04390.json · badge: /api/ran/2003.04390.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
cyvius96/few-shot-meta-baseline canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
mlpc-ucsd/ConstellationNet community (classifier label)
classifier basis: plan_row
0 ran · 2 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv1x1 Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/resnet12.py
code served (permissive licence) · get_code("de92832114f71d8c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/resnet12.py
code served (permissive licence) · get_code("e5b7c79b0b62af96")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv_block Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/convnet4.py
pointer only (licence: MIT); the stored copy get_code serves, from tiangeluo/fsl-global, is pointer only (licence: GPL-2.0) · get_code("9d556d61294bb0a8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tiangeluo/fsl-global, and GPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_nk_label Ran
ran on a synthesized input
cyvius96/few-shot-meta-baseline/utils/few_shot.py
code served (permissive licence) · get_code("a9882def8b5176d6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family int; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "n": 3,
    "k": 4,
    "ep_per_batch": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mean_confidence_interval Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from yinboc/few-shot-meta-baseline
pointer only · get_code("3233bdb56ef8b4da")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

norm_layer Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/resnet12.py
code served (permissive licence) · get_code("f36ac42575cd46ee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "planes": 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
register Ran
ran; our contract draft was wrong, not the code
cyvius96/few-shot-meta-baseline/meta-dataset/models/models.py
pointer only (licence: MIT); the stored copy get_code serves, from liyuantsao/flowsr-lp, is pointer only (licence: NONE) · get_code("44c3aa4c610ea3f7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from liyuantsao/flowsr-lp, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

split_shot_query Ran
ran on a synthesized input
cyvius96/few-shot-meta-baseline/utils/few_shot.py
code served (permissive licence) · get_code("2e717c371f330d15")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct valid arguments for split_shot_query
# The function expects:
# - data: a tensor that will be reshaped
# - way: number of ways (classes)
# - shot: number of shot samples
# - query: number of query samples
# - ep_per_batch: episodes per batch (default=1)

# The function does: data.view(ep_per_batch, way, shot + query, *img_shape)
# So data should have shape: (ep_per_batch * way * (shot + query), *img_shape)

ep_per_batch = 1
way = 3
shot = 2
query = 1
# img_shape will be (4, 5) - small spatial dimensions
img_shape = (4, 5)

# data needs shape (ep_per_batch * way * (shot + query), *img_shape)
# = (1 * 3 * (2 + 1), 4, 5) = (9, 4, 5)
data = torch.randn(9, 4, 5)

ARGS = {
    "data": data,
    "way": way,
    "shot": shot,
    "query": query,
    "ep_per_batch": ep_per_batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load Not yet run
unverified (harvested, no recorded run)
mlpc-ucsd/ConstellationNet/models/models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ggjy/vision_weak_to_strong, is pointer only (licence: NONE) · get_code("5bd23873a9c853d7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ggjy/vision_weak_to_strong, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

make Not yet run
unverified (harvested, no recorded run)
mlpc-ucsd/ConstellationNet/models/models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ggjy/vision_weak_to_strong, is pointer only (licence: NONE) · get_code("232045c11773f4a3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from ggjy/vision_weak_to_strong, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 10 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 9 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
59 dated earlier, 12 the same month, 359 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
30 dated earlier, 8 the same month, 273 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
register 24 other papers
24 later · 9 only as an assembly brick
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
2111.00195 (2021-11)
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
2111.08918 (2021-11)
Local Texture Estimator for Implicit Representation Function
and 21 more not named here
conv_block 11 other papers
3 dated earlier, 7 later, 1 same year, order not determinable
1703.05175 (2017-03)
Prototypical Networks for Few-shot Learning
1908.05257 (2019-08)
Few-Shot Learning with Global Class Representations
1911.06045 (2019-11)
Self-Supervised Learning For Few-Shot Image Classification
and 8 more not named here
conv1x1 5 other papers
5 later
2009.04960 (2020-09)
Prototype Completion with Primitive Knowledge for Few-Shot Learning
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
2312.00276 (2023-12)
Metalearning Continual Learning Algorithms
and 2 more not named here
conv3x3 5 other papers
5 later
2009.04960 (2020-09)
Prototype Completion with Primitive Knowledge for Few-Shot Learning
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
2312.00276 (2023-12)
Metalearning Continual Learning Algorithms
and 2 more not named here
norm_layer 4 other papers
4 later
2009.04960 (2020-09)
Prototype Completion with Primitive Knowledge for Few-Shot Learning
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
and 1 more not named here
load 2 other papers
2 later
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
2402.03749 (2024-02)
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
make 1 other paper
1 later
2402.03749 (2024-02)
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
mean_confidence_interval 1 other paper
1 dated earlier
1904.04232 (2019-04)
A Closer Look at Few-shot Classification

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear. In this paper, we explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard benchmarks. Our further analysis shed some light on understanding the trade-offs between the meta-learning objective and the whole-classification objective in few-shot learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.04390")
get_code_for_paper("2003.04390")
have("2003.04390")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.04390.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.04390.svg)](https://syntology.ai/paper/2003.04390)

Connect an agent — have() is free.