SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.08671 · 2022

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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 1 has 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/2206.08671.json · badge: /api/ran/2206.08671.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
cambridge-mlg/fit canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
cambridge-mlg/fit/src/bit_resnet.py
code served (permissive licence) · get_code("ee80cf467065076b")
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 StdConv2d. 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 = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'bias': False,
}
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 StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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
cambridge-mlg/fit/src/bit_resnet.py
code served (permissive licence) · get_code("f01b8d3901f0b289")
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 StdConv2d. 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 = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'groups': 1,
    'bias': False,
}
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 StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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
drop_connect Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cambridge-mlg/fit/src/efficientnet_utils.py
code served (permissive licence) · get_code("d3319e3d34ca90ca")
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 4, dtype family float, shape (2, 4, 3, 5) 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 small input tensor with shape BCWH (Batch, Channels, Width, Height)
# Using batch_size=2, channels=4, width=3, height=5 for distinct dimensions
inputs = torch.randn(2, 4, 3, 5, dtype=torch.float32)

# Probability of drop connection
p = 0.5

# Training mode flag
training = True

ARGS = {
    "inputs": inputs,
    "p": p,
    "training": training
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
film Ran
ran on a synthesized input
cambridge-mlg/fit/src/efficientnet.py
code served (permissive licence) · get_code("a0c64af1bc66fb1f")
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 4, dtype family float, shape (2, 4, 3, 5) 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)

# Construct arguments for film(x, gamma, beta)
# The function expects:
# - x: a tensor that will be reshaped with [None, :, None, None] operations on gamma and beta
#   so x should be 4D (batch, channels, height, width)
# - gamma: a 1D tensor of shape (channels,)
# - beta: a 1D tensor of shape (channels,)

x = torch.randn(2, 4, 3, 5)  # batch=2, channels=4, height=3, width=5
gamma = torch.randn(4)        # channels=4
beta = torch.randn(4)         # channels=4

ARGS = {
    "x": x,
    "gamma": gamma,
    "beta": beta,
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
round_filters Ran
ran; our contract draft was wrong, not the code
cambridge-mlg/fit/src/efficientnet_utils.py
code served (permissive licence) · get_code("f15a49337e69e937")
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 int, ndim 0, dtype family int, 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.

from collections import namedtuple

# Create a namedtuple for global_params with the required attributes
GlobalParams = namedtuple('GlobalParams', ['width_coefficient', 'depth_divisor', 'min_depth'])

# Create valid global_params instance
global_params = GlobalParams(
    width_coefficient=1.0,
    depth_divisor=8,
    min_depth=16
)

ARGS = {
    'filters': 32,
    'global_params': global_params
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
round_repeats Ran
ran; our contract draft was wrong, not the code
cambridge-mlg/fit/src/efficientnet_utils.py
code served (permissive licence) · get_code("dbc0ca08d119a5a0")
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 int, ndim 0, dtype family int, 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.

from collections import namedtuple

# Create a namedtuple for global_params with the depth_coefficient attribute
GlobalParams = namedtuple('GlobalParams', ['depth_coefficient'])

# Define ARGS with valid arguments for round_repeats
ARGS = {
    'repeats': 4,
    'global_params': GlobalParams(depth_coefficient=1.5)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
tf2th Ran
ran, violated the contract we drafted
cambridge-mlg/fit/src/bit_resnet.py
code served (permissive licence) · get_code("7023eb86801bb3a3")
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 4, dtype family float, shape (6, 5, 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
import numpy as np

torch.manual_seed(0)

# Create a 4D numpy array in HWIO format (Height, Width, Input channels, Output channels)
# Using distinct dimensions: H=3, W=4, I=5, O=6
conv_weights = np.random.randn(3, 4, 5, 6).astype(np.float32)

ARGS = {
    "conv_weights": conv_weights
}
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 4, dtype family float, shape (6, 5, 3, 4) — shape (6, 5, 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
create_film_adapter Not yet run
unverified (harvested, no recorded run)
cambridge-mlg/fit/src/features.py
code served (permissive licence) · get_code("2c33452dc3252bdd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 2 the same month, 6 later) and 1 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 33 other papers
17 dated earlier, 1 the same month, 15 later · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
conv3x3 33 other papers
17 dated earlier, 1 the same month, 15 later · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
round_filters 31 other papers
21 dated earlier, 10 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 28 more not named here
round_repeats 30 other papers
22 dated earlier, 8 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 27 more not named here
drop_connect 23 other papers
9 dated earlier, 14 later · 2 only as an assembly brick
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1912.01588 (2019-12)
Leveraging Procedural Generation to Benchmark Reinforcement Learning
2010.00475 (2020-10)
FSD50K: An Open Dataset of Human-Labeled Sound Events
and 20 more not named here
tf2th 17 other papers
8 dated earlier, 9 later
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2104.02610 (2021-04)
On the Robustness of Vision Transformers to Adversarial Examples
2106.01127 (2021-06)
Towards Robust Classification Model by Counterfactual and Invariant Data Generation
and 14 more not named here
film 1 other paper
1 dated earlier
2107.01105 (2021-07)
Memory Efficient Meta-Learning with Large Images

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

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training protocols. In this work, we develop FiLM Transfer (FiT) which fulfills these requirements in the image classification setting by combining ideas from transfer learning (fixed pretrained backbones and fine-tuned FiLM adapter layers) and meta-learning (automatically configured Naive Bayes classifiers and episodic training) to yield parameter efficient models with superior classification accuracy at low-shot. The resulting parameter efficiency is key for enabling few-shot learning, inexpensive model updates for personalization, and communication efficient federated learning. We experiment with FiT on a wide range of downstream datasets and show that it achieves better classification accuracy than the leading Big Transfer (BiT) algorithm at low-shot and achieves state-of-the art accuracy on the challenging VTAB-1k benchmark, with fewer than 1% of the updateable parameters. Finally, we demonstrate the parameter efficiency and superior accuracy of FiT in distributed low-shot applications including model personalization and federated learning where model update size is an important performance metric.

For agents

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

get_harvested_code_for_paper("2206.08671")
get_code_for_paper("2206.08671")
have("2206.08671")

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

curl https://syntology.ai/api/ran/2206.08671.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.08671.svg)](https://syntology.ai/paper/2206.08671)

Connect an agent — have() is free.