Papers › Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

20 Jul 2022arXiv:2207.10077archive 2025-07-28

Zhiheng Li, Anthony Hoogs, Chenliang Xu

Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as full-supervision, which has two limitations: 1) it is infeasible when the labels are unavailable; 2) they are incapable of mitigating unknown biases -- biases that humans do not preconceive. To resolve those problems, we propose Debiasing Alternate Networks (DebiAN), which comprises two networks -- a Discoverer and a Classifier. By training in an alternate manner, the discoverer tries to find multiple unknown biases of the classifier without any annotations of biases, and the classifier aims at unlearning the biases identified by the discoverer. While previous works evaluate debiasing results in terms of a single bias, we create Multi-Color MNIST dataset to better benchmark mitigation of multiple biases in a multi-bias setting, which not only reveals the problems in previous methods but also demonstrates the advantage of DebiAN in identifying and mitigating multiple biases simultaneously. We further conduct extensive experiments on real-world datasets, showing that the discoverer in DebiAN can identify unknown biases that may be hard to be found by humans. Regarding debiasing, DebiAN achieves strong bias mitigation performance.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2207.10077")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhihengli-UR/DebiAN officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 2 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran
7unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhihengli-UR/DebiAN. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ReturnFeatureLinear zhihengli-UR/DebiAN/celeba_exp/debian.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · d7064f35905da759 · report
get_transform_face zhihengli-UR/DebiAN/celeba_exp/debian.py official repository ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · a4121c87206a8780 · report
BaseFaceTrainer zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · 771e469ce3972241 · report
CelebA zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · 163c69a1ce33abba · report
Trainer zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · a9605d7cedee1478 · report
get_attr_names zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · 9243b4c9feba0f83 · report
get_resnet18_classifier zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · 262ebea7bbe1f644 · report
get_resnet50_classifier zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · c2d20296f8de6e27 · report
get_train_val_test zhihengli-UR/DebiAN/celeba_exp/debian.py official repository unverified GPL-3.0 (copyleft) · pointer only · a128f28e60438084 · report

Tasks

Action RecognitionFacial Attribute ClassificationOut-of-Distribution Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition BAR DebiAN Accuracy 69.88 #1 of 4 Archive leaderboard report
Facial Attribute Classification bFFHQ DebiAN Bias-Conflicting Accuracy 62.8 #1 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections