SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06606 · CVPR · 2024

Distributionally Generative Augmentation for Fair Facial Attribute Classification

Hanwang Zhang, Jiashuo Liu, Chao Wu, Long Chen, Jun Xiao, Kun Kuang, Fengda Zhang, Qianpei He

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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, 2 violated it and 0 have no contract verdict; 6 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/2403.06606.json · badge: /api/ran/2403.06606.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
heqianpei/DiGA canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
bayes_neg Ran
ran, honoured the contract we drafted
heqianpei/DiGA/BayesClassifier.py
pointer only (licence: NONE) · get_code("50ff2f1fe67f4281")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

bayes_pos Ran
ran, honoured the contract we drafted
heqianpei/DiGA/BayesClassifier.py
pointer only (licence: NONE) · get_code("9b3d118b4894317f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

default Ran
ran, violated the contract we drafted
heqianpei/DiGA/BYOL/BYOL.py
pointer only (licence: NONE) · get_code("1c0f269ae9673b08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

get_keys Ran
ran; our contract draft was wrong, not the code
heqianpei/DiGA/models/psp.py
pointer only (licence: NONE) · get_code("29b9a890f149a3a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

get_latent_code Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
heqianpei/DiGA/boundary/get_latent_codes.py
pointer only (licence: NONE) · get_code("2df912740aaa5bb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

get_latents Ran
ran; our contract draft was wrong, not the code
heqianpei/DiGA/boundary/get_latent_codes.py
pointer only (licence: NONE) · get_code("c6cacd2f9fa3185e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

get_module_device Ran
ran; our contract draft was wrong, not the code
heqianpei/DiGA/BYOL/BYOL.py
pointer only (licence: NONE) · get_code("f8ef5ca2539fcee5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

get_result Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
heqianpei/DiGA/BYOL/train_LC.py
pointer only (licence: NONE) · get_code("4d741352ba58146a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

loss_fn Ran
ran; our contract draft was wrong, not the code
heqianpei/DiGA/BYOL/BYOL.py
pointer only (licence: NONE); the stored copy get_code serves, from Namkyeong/BGRL_Pytorch, is pointer only (licence: NONE) · get_code("00cae89471470576")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

pdf Ran
ran, violated the contract we drafted
heqianpei/DiGA/BayesClassifier.py
pointer only (licence: NONE) · get_code("122622470a5e44e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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.

train_model Not yet run
unverified (harvested, no recorded run)
heqianpei/DiGA/BYOL/train_LC.py
pointer only (licence: NONE) · get_code("dc0ca3f84b19d396")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, heqianpei/DiGA 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 7 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
get_keys 14 other papers
12 dated earlier, 2 later
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
2011.12799 (2020-11)
StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
2103.17249 (2021-03)
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
and 11 more not named here
default 11 other papers
11 dated earlier
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2010.10241 (2020-10)
BYOL works even without batch statistics
2011.10043 (2020-11)
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
and 8 more not named here
loss_fn 7 other papers
6 dated earlier, 1 later · 3 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2021.acl-long.402 (2021 (year only))
Bootstrapped Unsupervised Sentence Representation Learning
2102.06514 (2021-02)
Large-Scale Representation Learning on Graphs via Bootstrapping
and 4 more not named here
get_module_device 5 other papers
4 dated earlier, 1 later · 3 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2102.12122 (2021-02)
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
2103.15358 (2021-03)
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding
and 2 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

Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting accuracy inconsistencies across varied data subpopulations. This unfairness is largely attributed to bias in data, where some spurious attributes (e.g., Male) statistically correlate with the target attribute (e.g., Smiling). Most of existing fairness-aware methods rely on the labels of spurious attributes, which may be unavailable in practice. This work proposes a novel, generation-based twostage framework to train a fair FAC model on biased data without additional annotation. Initially, we identify the potential spurious attributes based on generative models. Notably, it enhances interpretability by explicitly showing the spurious attributes in image space. Following this, for each image, we first edit the spurious attributes with a random degree sampled from a uniform distribution, while keeping target attribute unchanged. Then we train a fair FAC model by fostering model invariance to these augmentation. Extensive experiments on three common datasets demonstrate the effectiveness of our method in promoting fairness in FAC without compromising accuracy. Codes are in https://github.com/heqianpei/DiGA.

For agents

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

get_harvested_code_for_paper("2403.06606")
get_code_for_paper("2403.06606")
have("2403.06606")

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

curl https://syntology.ai/api/ran/2403.06606.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06606.svg)](https://syntology.ai/paper/2403.06606)

Connect an agent — have() is free.