SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09176 · ECCV · 2022

Self-Supervision Can Be a Good Few-Shot Learner

Liangjian Wen, Jianzhuang Liu, Xinmei Tian, Yuning Lu, Yajing Liu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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; 3 failures of our instrument; 5 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/2207.09176.json · badge: /api/ran/2207.09176.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
bbbdylan/unisiam canonical (classifier label)
classifier basis not recorded on the link
3 ran · 5 no recorded run
yangyucheng000/MSpaper community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
bbbdylan/unisiam/model/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
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 medaitech/scrd4ad, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
bbbdylan/unisiam/model/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
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 medaitech/scrd4ad, 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.

sigmoid Ran
ran on a synthesized input
yangyucheng000/MSpaper/UNet3+/eval_onnx.py
code served (permissive licence) · get_code("71f6b54bb153195b")
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 ndarray, ndim 2, dtype family float, shape (2, 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 numpy as np

# Create a small numpy array with both negative and positive values
# This tests both branches of the sigmoid function
prediction = np.array([[-2.0, -0.5, 0.5, 2.0],
                       [-1.0, 0.0, 1.0, 3.0]], dtype=np.float32)

ARGS = {
    "prediction": prediction
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
sigmoid Ran
ran, violated the contract we drafted
yangyucheng000/MSpaper/UNet3+/postprocess.py
code served (permissive licence) · get_code("35f8386d0382d374")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

def sigmoid(z):
    """define sigmoid"""
    return 1 / (1 + np.exp(-z))

# Create a small numpy array to pass to sigmoid
z_value = np.array([0.0, 1.0, -1.0, 2.0])

ARGS = {
    "z": z_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
translate_x_rel Ran
ran; our contract draft was wrong, not the code
bbbdylan/unisiam/transform/rand_augmentation.py
pointer only (licence: MIT); the stored copy get_code serves, from tongzixin716716/Inverse-Loss-Reweighting, is pointer only (licence: NONE) · get_code("a4b471197204b414")
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 tongzixin716716/Inverse-Loss-Reweighting, 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.

accuracy Not yet run
unverified (harvested, no recorded run)
bbbdylan/unisiam/util.py
pointer only (licence: MIT); the stored copy get_code serves, from boone891214/MEST, is pointer only (licence: NONE) · get_code("913d82af53065418")
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 boone891214/MEST, 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.

build_transform Not yet run
unverified (harvested, no recorded run)
bbbdylan/unisiam/transform/build_transform.py
code served (permissive licence) · get_code("830d602b5d97e75d")
How it ran

no invocation recorded.

resnet10 Not yet run
unverified (harvested, no recorded run)
bbbdylan/unisiam/model/resnet.py
code served (permissive licence) · get_code("b8f8a709e70fae66")
How it ran

no invocation recorded.

shear_x Not yet run
unverified (harvested, no recorded run)
bbbdylan/unisiam/transform/rand_augmentation.py
pointer only (licence: MIT); the stored copy get_code serves, from tongzixin716716/Inverse-Loss-Reweighting, is pointer only (licence: NONE) · get_code("7b4e3d0bd192b677")
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 tongzixin716716/Inverse-Loss-Reweighting, 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.

shear_y Not yet run
unverified (harvested, no recorded run)
bbbdylan/unisiam/transform/rand_augmentation.py
pointer only (licence: MIT); the stored copy get_code serves, from tongzixin716716/Inverse-Loss-Reweighting, is pointer only (licence: NONE) · get_code("e31c4b500a240e69")
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 tongzixin716716/Inverse-Loss-Reweighting, 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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, 7 later) and 3 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 112 other papers
25 dated earlier, 1 the same month, 85 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
22 dated earlier, 4 the same month, 84 later, 1 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
accuracy 80 other papers
64 dated earlier, 15 later, 1 same year, order not determinable
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 more not named here
shear_x 27 other papers
6 dated earlier, 19 later, 2 same year, order not determinable
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
shear_y 27 other papers
6 dated earlier, 19 later, 2 same year, order not determinable
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
translate_x_rel 26 other papers
6 dated earlier, 18 later, 2 same year, order not determinable
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 23 more not named here
sigmoid 7 other papers
2 dated earlier, 5 later
2006.06887 (2020-06)
Stochastic Optimization for Performative Prediction
2007.13819 (2020-07)
MULTI-LEVEL LOCAL SGD: DISTRIBUTED SGD FOR HETEROGENEOUS HIERARCHICAL NETWORKS
2402.14992 (2024-02)
tinyBenchmarks: evaluating LLMs with fewer examples
and 4 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

Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic perspective, we propose an effective unsupervised FSL method, learning representations with self-supervision. Following the InfoMax principle, our method learns comprehensive representations by capturing the intrinsic structure of the data. Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform selfsupervised pre-training. Rather than supervised pre-training focusing on the discriminable features of the seen classes, our self-supervised model has less bias toward the seen classes, resulting in better generalization for unseen classes. We explain that supervised pre-training and selfsupervised pre-training are actually maximizing different MI objectives. Extensive experiments are further conducted to analyze their FSL performance with various training settings. Surprisingly, the results show that self-supervised pre-training can outperform supervised pre-training under the appropriate conditions. Compared with state-of-the-art FSL methods, our approach achieves comparable performance on widely used FSL benchmarks without any labels of the base classes.

For agents

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

get_harvested_code_for_paper("2207.09176")
get_code_for_paper("2207.09176")
have("2207.09176")

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

curl https://syntology.ai/api/ran/2207.09176.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.09176.svg)](https://syntology.ai/paper/2207.09176)

Connect an agent — have() is free.