Gender Classification

Benchmarks

Dataset Name	SOTA Method	Metric
COCO 95% spurious correlation	BAP	Average Score78.1	24	2mo ago
MS COCO subset (test)		FFP22	23	4mo ago
ABCD	BrainWorld F+S-prior	Accuracy80.75	22	1mo ago
COCO 100% spurious correlation	BAP	Average Score77.9	20	2mo ago
FairFace v1 (test)	CLIP + MT + NL + EDL	Accuracy (Black)95.37	20	4mo ago
Combined speech dataset (Baker, LJSpeech, ESD, CREMA-D, Genshin Impact) 1.0 (subject-independent)	ParaMETA	Balanced Acc0.784	19	4mo ago
Adience (cross-validation)	RoR-34+ IMDB-WIKI	Exact Accuracy93.24	18	4mo ago
FairFace (test)	Image-Text Fusion - T1	Overall Accuracy87.67	15	1mo ago
UTKFace (test)	VOLO-D1 face	Gender Accuracy98.87	14	3mo ago
BHRC	BrainWorld F+S-prior	Accuracy79.94	12	1mo ago
Internal (test)	BNT	Accuracy71.91	12	4mo ago
HCP Gender n=999 (5-fold cross-validation)	Artemis	Accuracy86.7	11	1mo ago
Census Adult UCI (test)		Mean Accuracy75.63	10	1mo ago
AudioMNIST	CDIG	Faithfulness60.3	10	2mo ago
Zappos50k in-domain (test)	MSCon	Top-1 Accuracy85.98	10	4mo ago
DiveFace (test)	CLIP	Accuracy (East Asian Male)97.371	9	4mo ago
UTKFace	FairNVT	Accuracy97.7	9	3mo ago
Morph (Cross-dataset)	CLIP + LP	DoB0.89	9	4mo ago
DiveFace (Cross-dataset)	MT + NL + EDL	DoB0.83	9	4mo ago
UTKFace Cross-dataset	CLIP + NL	DoB1.6	9	4mo ago
CelebA Out-of-distribution Blonde Hair Shortcut (test)	Coop-CBM	Accuracy82	8	4mo ago
CelebA In-distribution Blonde Hair Shortcut (test)		Accuracy96.5	8	4mo ago
OPERA Gender Cough (Split 2)	OCT	AUROC0.874	7	4mo ago
OPERA Gender Cough (1)	AcuLa	AUROC0.796	7	4mo ago
FairFace level-5 Gaussian noise corrupted (test)	FairSAM	Accuracy (s+)63.7	6	1mo ago

Showing 25 of 58 rows