SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_26699 · AAAI · 2023

MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition

Min Sun, Chien-Yi Wang, Shang-Hong Lai, Fu-En Wang

Code that ran

8 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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/aaai_26699.json · badge: /api/ran/aaai_26699.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
fuenwang/MixFairFace canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
FunctionStatusWhere it lives
ReadImage Ran
ran on a synthesized input
fuenwang/MixFairFace/MixFairFace/Datasets/SharedFunctions.py
code served (permissive licence) · get_code("eb0ad57af3b4d7e2")
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 3, dtype family float, shape (4, 3, 3) 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 cv2
import numpy as np
import tempfile
import os
from PIL import Image

# Create a temporary directory and a small test image
temp_dir = tempfile.mkdtemp()
test_image_path = os.path.join(temp_dir, "test_image.png")

# Create a small RGB image (10x8 pixels) and save it
test_img = Image.new('RGB', (10, 8), color=(255, 100, 50))
test_img.save(test_image_path)

# Define the arguments dictionary
ARGS = {
    'path': test_image_path,
    'shape': (4, 3)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, imageio, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 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
calculate_accuracy Ran
ran, honoured the contract we drafted
fuenwang/MixFairFace/MixFairFace/Verify/RFW.py
pointer only (licence: MIT); the stored copy get_code serves, from zrui94/insight_mx, is pointer only (licence: NONE) · get_code("f975336b5d5f1a80")
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 zrui94/insight_mx, 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.

calculate_roc Ran
ran on a synthesized input
fuenwang/MixFairFace/MixFairFace/Verify/RFW.py
code served (permissive licence) · get_code("c3af5327e1b4e163")
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 numpy as np

# Set seed for reproducibility
np.random.seed(42)

# Create small test data
nrof_samples = 10
embedding_dim = 4
nrof_thresholds = 5

# Create embeddings1 and embeddings2
embeddings1 = np.random.randn(nrof_samples, embedding_dim).astype(np.float32)
embeddings2 = np.random.randn(nrof_samples, embedding_dim).astype(np.float32)

# Create actual_issame boolean array
actual_issame = np.array([True, False, True, False, True, False, True, False, True, False], dtype=bool)

# Create thresholds
thresholds = np.linspace(0, 10, nrof_thresholds)

ARGS = {
    "thresholds": thresholds,
    "embeddings1": embeddings1,
    "embeddings2": embeddings2,
    "actual_issame": actual_issame,
    "nrof_folds": 2,
    "pca": 0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
fuenwang/MixFairFace/MixFairFace/IResNet.py
code served (permissive licence) · get_code("158bf4c3a5f11f04")
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
from torch import nn

torch.manual_seed(0)

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
conv3x3 Ran
ran; our contract draft was wrong, not the code
fuenwang/MixFairFace/MixFairFace/IResNet.py
code served (permissive licence) · get_code("29df79c9fdb0cee8")
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
cosine_sim Ran
ran; our contract draft was wrong, not the code
fuenwang/MixFairFace/MixFairFace/CosFace.py
code served (permissive licence) · get_code("55b7eacdfa96a1c5")
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 (2, 3) 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 two small tensors for cosine similarity computation
# x1: shape (2, 4) - 2 samples, 4 dimensions
# x2: shape (3, 4) - 3 samples, 4 dimensions
x1 = torch.randn(2, 4)
x2 = torch.randn(3, 4)

ARGS = {
    "x1": x1,
    "x2": x2,
    "dim": 1,
    "eps": 1e-08
}
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 (2, 3) — shape (2, 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
count_parameters Ran
ran, honoured the contract we drafted
fuenwang/MixFairFace/MixFairFace/Tools.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 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
normalizeDepth Ran
ran on a synthesized input
fuenwang/MixFairFace/MixFairFace/Tools.py
code served (permissive licence) · get_code("9ac2a3c4a05a69ae")
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)

# The function normalizeDepth expects a tensor with a batch dimension
# It iterates over the first dimension (batch), clones the tensor,
# subtracts the min and divides by max for each batch element
# So we need a multi-dimensional tensor with batch size > 0

depth = torch.randn(2, 4, 3, 5)  # batch=2, distinct dimensions for probing

ARGS = {
    "depth": depth
}
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
PrepareDataset Not yet run
unverified (harvested, no recorded run)
fuenwang/MixFairFace/MixFairFace/FairnessTrainer.py
code served (permissive licence) · get_code("a2c2ad89ea421903")
How it ran

no invocation recorded.

calculate_val Not yet run
unverified (harvested, no recorded run)
fuenwang/MixFairFace/MixFairFace/Verify/RFW.py
code served (permissive licence) · get_code("971b2f11a6d034df")
How it ran

no invocation recorded.

iresnet18 Not yet run
unverified (harvested, no recorded run)
fuenwang/MixFairFace/MixFairFace/IResNet.py
code served (permissive licence) · get_code("e80eb3ca0b032b9c")
How it ran

no invocation recorded.

rgetattr Not yet run
unverified (harvested, no recorded run)
fuenwang/MixFairFace/MixFairFace/Tools.py
code served (permissive licence) · get_code("44925cf3831bfe79")
How it ran

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, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 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 431 other papers
236 dated earlier, 118 later, 76 same year, order not determinable, 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
152 dated earlier, 98 later, 61 same year, order not determinable, 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
count_parameters 180 other papers
78 dated earlier, 67 later, 35 same year, order not determinable · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
rgetattr 13 other papers
4 dated earlier, 5 later, 4 same year, order not determinable · 1 only as an assembly brick
2203.04036 (2022-03)
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
2209.02952 (2022-09)
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
2211.05778 (2022-11)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
and 10 more not named here
calculate_accuracy 12 other papers
10 dated earlier, 2 later
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1607.08221 (2016-07)
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
1703.07737 (2017-03)
In Defense of the Triplet Loss for Person Re-Identification
and 9 more not named here
iresnet18 6 other papers
1 dated earlier, 4 later, 1 same year, order not determinable
aaai_20057 (2022 (year only))
FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition
2308.04995 (2023-08)
IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models
2404.06025 (2024-04)
Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
and 3 more not named here
cosine_sim 2 other papers
1 dated earlier, 1 later
1904.02882 (2019-04)
LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
2404.13788 (2024-04)
AnyPattern: Towards In-context Image Copy Detection
normalizeDepth 2 other papers
2 dated earlier
2104.00568 (2021-04)
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
2209.02952 (2022-09)
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
calculate_roc 1 other paper
1 dated earlier
2004.01461 (2020-04)
Gradient Centralization: A New Optimization Technique for Deep Neural Networks

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

Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.

For agents

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

get_harvested_code_for_paper("aaai_26699")
get_code_for_paper("aaai_26699")
have("aaai_26699")

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

curl https://syntology.ai/api/ran/aaai_26699.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_26699.svg)](https://syntology.ai/paper/aaai_26699)

Connect an agent — have() is free.