SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.04960 · 2020

Prototype Completion with Primitive Knowledge for Few-Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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, 0 violated it and 7 have no contract verdict; 5 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2009.04960.json · badge: /api/ran/2009.04960.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
zhangbq-research/Prototype_Completion_for_FSL canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
CosineNetHead Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/models/classification_heads.py
code served (permissive licence) · get_code("068a0a6a30e1e25c")
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 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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)

# Build a minimal meta_part_infer model that satisfies the function's usage
class MetaPartInfer(nn.Module):
    def __init__(self, d):
        super().__init__()
        self.d = d
    
    def forward(self, x, k, is_infer=False):
        # Function calls: meta_part_infer(prototypes.reshape(-1, d), k_all.reshape(-1), is_infer=is_scale)
        # Returns two values: boost_prototypes and something else (ignored via _)
        # x shape: (tasks_per_batch * n_way, d)
        # k shape: (tasks_per_batch * n_way,)
        # Returns: (tasks_per_batch * n_way, d), and anything else
        boosted = x * 1.1  # Simple scaling operation
        return boosted, None

# Set dimensions with distinct sizes
tasks_per_batch = 2
n_way = 3
n_shot = 2
n_support = n_way * n_shot  # 6
n_query = 4
d = 5  # embedding dimension

# Create tensors
query = torch.randn(tasks_per_batch, n_query, d)
support = torch.randn(tasks_per_batch, n_support, d)
support_labels = torch.randint(0, n_way, (tasks_per_batch, n_support))
k_all = torch.randn(tasks_per_batch, n_way)

# Create the meta_part_infer model
meta_part_infer = MetaPartInfer(d)

ARGS = {
    'k_all': k_all,
    'meta_part_infer': meta_part_infer,
    'query': query,
    'support': support,
    'support_labels': support_labels,
    'n_way': n_way,
    'n_shot': n_shot,
    'is_scale': False,
    'normalize': True,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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 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
CosineNetHead Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/models/classification_heads_orgin.py
code served (permissive licence) · get_code("4ec52ee88c7bc858")
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 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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)

# Parameters for CosineNetHead
tasks_per_batch = 2
n_way = 3
n_shot = 2
n_support = n_way * n_shot
n_query = 4
d = 5

# Create query tensor: (tasks_per_batch, n_query, d)
query = torch.randn(tasks_per_batch, n_query, d)

# Create support tensor: (tasks_per_batch, n_support, d)
support = torch.randn(tasks_per_batch, n_support, d)

# Create support_labels tensor: (tasks_per_batch, n_support)
# Labels should be in range [0, n_way)
support_labels = torch.tensor([
    [0, 0, 1, 1, 2, 2],
    [0, 0, 1, 1, 2, 2]
], dtype=torch.long)

ARGS = {
    "query": query,
    "support": support,
    "support_labels": support_labels,
    "n_way": n_way,
    "n_shot": n_shot,
    "normalize": True
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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 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
FuseCosineNetHead Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/models/classification_heads.py
code served (permissive licence) · get_code("f7312cd2956a3b29")
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 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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)

# Parameters for FuseCosineNetHead
tasks_per_batch = 2
n_way = 3
n_shot = 2
n_support = n_way * n_shot  # 6
n_query = 4
d = 5  # embedding dimension

# Create query tensor: (tasks_per_batch, n_query, d)
query = torch.randn(tasks_per_batch, n_query, d)

# Create support tensor: (tasks_per_batch, n_support, d)
support = torch.randn(tasks_per_batch, n_support, d)

# Create support_labels tensor: (tasks_per_batch, n_support)
# Labels should be in range [0, n_way)
support_labels = torch.tensor([
    [0, 0, 1, 1, 2, 2],
    [0, 0, 1, 1, 2, 2]
], dtype=torch.long)

# Create k_all tensor
k_all = torch.randn(tasks_per_batch, n_way)

# Create meta_part_infer mock module
class MetaPartInfer(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(d, d)
    
    def forward(self, x, k, use_scale=False, is_infer=False):
        # x shape: (tasks_per_batch * n_way, d)
        # k shape: (tasks_per_batch * n_way,)
        output = self.linear(x)
        if use_scale and is_infer:
            return output, torch.randn(x.size(0))
        else:
            return (output,)

meta_part_infer = MetaPartInfer()

# Prepare arguments dictionary
ARGS = {
    'k_all': k_all,
    'meta_part_infer': meta_part_infer,
    'query': query,
    'support': support,
    'support_labels': support_labels,
    'n_way': n_way,
    'n_shot': n_shot,
    'is_scale': False,
    'normalize': True
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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 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
constructedges Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/prior/make_miniimagenet_primitive_knowledge.py
code served (permissive licence) · get_code("161f62eb1a752b4c")
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 list, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. 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

# Construct a small dictionary mapping synonym IDs to integers
# This represents a mapping from synonym strings to their integer IDs
syns2id = {
    'syn_a': 0,
    'syn_b': 1,
    'syn_c': 2,
    'syn_d': 3,
}

# Construct a dictionary where keys are synonyms and values are lists of related synonyms
# This represents a graph where each synonym points to other synonyms
s = {
    'syn_a': ['syn_b', 'syn_c'],
    'syn_b': ['syn_d'],
    'syn_c': ['syn_a'],
}

ARGS = {
    's': s,
    'syns2id': syns2id,
}
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 list, ndim 2, dtype family int — a list output has no array shape of its own; none is stated
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 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
zhangbq-research/Prototype_Completion_for_FSL/models/resnet12_2.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
zhangbq-research/Prototype_Completion_for_FSL/models/resnet12_2.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
count_accuracy Ran
ran; our contract draft was wrong, not the code
zhangbq-research/Prototype_Completion_for_FSL/utils.py
code served (permissive licence) · get_code("fb61241b42c06d73")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Create small tensors for testing count_accuracy
# logits: shape (batch_size, num_classes) - the function does argmax on dim=1
# label: shape (batch_size,) - the function views it as -1

batch_size = 2
num_classes = 4

# Create logits tensor with shape (2, 4)
logits = torch.randn(batch_size, num_classes)

# Create label tensor with shape (2,) containing class indices
label = torch.tensor([0, 1])

ARGS = {
    "logits": logits,
    "label": label,
}
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 0, dtype family float, shape () — shape () as a later run recorded it
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 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
getwnid Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/prior/make_miniimagenet_primitive_knowledge.py
code served (permissive licence) · get_code("212f1ff29913b717")
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 str. 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

# The function calls u.offset() and expects it to return an integer
# We need to create a mock object with an offset() method

class MockWordNetObject:
    def __init__(self, offset_value):
        self._offset = offset_value
    
    def offset(self):
        return self._offset

# Create a mock object with a reasonable offset value
# Using a small integer that will test the zero-padding logic
u = MockWordNetObject(12345)

ARGS = {
    'u': u
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
l2_loss Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/utils.py
code served (permissive licence) · get_code("78ac9e19f328f531")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

torch.manual_seed(0)

# The function l2_loss takes two arguments (a, b) and computes:
# ((a - b) ** 2).sum() / (len(a) * 2)
# Both a and b need to support:
# - subtraction (a - b)
# - exponentiation (** 2)
# - .sum() method
# - len() function
# This works with torch tensors

a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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 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
norm_layer Ran
ran; our contract draft was wrong, not the code
zhangbq-research/Prototype_Completion_for_FSL/models/resnet12_2.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
one_hot Ran
ran; our contract draft was wrong, not the code
zhangbq-research/Prototype_Completion_for_FSL/models/classification_heads.py
code served (permissive licence) · get_code("7c64c35be7f02395")
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 Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. 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)

# Create a small indices tensor with shape (2, 3)
# Values should be in range [0, depth)
indices = torch.tensor([[0, 1, 2], [1, 2, 0]], dtype=torch.long)

# Depth parameter - number of one-hot classes
depth = 4

ARGS = {
    "indices": indices,
    "depth": depth,
}
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 Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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 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
pick_vectors Ran
ran on a synthesized input
zhangbq-research/Prototype_Completion_for_FSL/utils.py
code served (permissive licence) · get_code("a2b31023f6121fdf")
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 2, dtype family float, shape (3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Create a dictionary mapping wnids (WordNet IDs) to vectors
# The function expects dic to have numeric vectors as values
dic = {
    'wnid_1': [1.0, 2.0, 3.0, 4.0],
    'wnid_2': [5.0, 6.0, 7.0, 8.0],
    'wnid_3': [9.0, 10.0, 11.0, 12.0],
}

# List of wnids to pick from the dictionary
# Some exist in dic, some don't (to test the None case)
wnids = ['wnid_1', 'wnid_missing', 'wnid_3']

# Test with is_tensor=False (default behavior)
# This creates list vectors in the dictionary
ARGS = {
    'dic': dic,
    'wnids': wnids,
    'is_tensor': False,
}
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 2, dtype family float, shape (3, 4) — shape (3, 4) as a later run recorded it
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 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
getnode Not yet run
unverified (harvested, no recorded run)
zhangbq-research/Prototype_Completion_for_FSL/prior/make_miniimagenet_primitive_knowledge.py
code served (permissive licence) · get_code("0c7425262620b51b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 5 later) and 8 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
one_hot 11 other papers
1 dated earlier, 9 later, 1 same year, order not determinable · 4 only as an assembly brick
1703.05175 (2017-03)
Prototypical Networks for Few-shot Learning
ijcai2020_0377 (2020 (year only))
Consistent MetaReg: Alleviating Intra-task Discrepancy for Better Meta-knowledge
2010.07092 (2020-10)
Data Augmentation for Meta-Learning
and 8 more not named here
conv1x1 5 other papers
1 dated earlier, 4 later
2003.04390 (2020-03)
Meta-Baseline: Exploring Simple Meta-Learning 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
1 dated earlier, 4 later
2003.04390 (2020-03)
Meta-Baseline: Exploring Simple Meta-Learning 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
count_accuracy 4 other papers
4 later
2010.07092 (2020-10)
Data Augmentation for Meta-Learning
2111.04316 (2021-11)
SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning
2211.14666 (2022-11)
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
and 1 more not named here
norm_layer 4 other papers
1 dated earlier, 3 later
2003.04390 (2020-03)
Meta-Baseline: Exploring Simple Meta-Learning 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

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 2026-11-22.

Repositories linked to this paper

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

Abstract

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.

For agents

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

get_harvested_code_for_paper("2009.04960")
get_code_for_paper("2009.04960")
have("2009.04960")

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

curl https://syntology.ai/api/ran/2009.04960.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.04960.svg)](https://syntology.ai/paper/2009.04960)

Connect an agent — have() is free.