---
language:
  - en
license: cc-by-4.0
library_name: pytorch
pipeline_tag: image-classification
tags:
  - image-classification
  - fairface
  - face-attribute
  - pytorch
  - timm
datasets:
  - HuggingFaceM4/FairFace
base_model: timm/eva02_large_patch14_224.mim_in22k
metrics:
  - accuracy
  - f1
---
# FairFace-MonkeyCake-3Task-224

## Overview

A multi-task face attribute classification model based on **EVA02-L/14 (MIM-22K)** ([timm/eva02_large_patch14_224.mim_in22k](https://huggingface.co/timm/eva02_large_patch14_224.mim_in22k)), trained on the [HuggingFaceM4/FairFace](https://huggingface.co/datasets/HuggingFaceM4/FairFace) dataset.
Predicts three demographic attributes simultaneously: race, gender, and age.

> Teacher model with highest overall accuracy; 303M parameters and 344 img/s. Best suited for offline benchmarking rather than real-time edge deployment.

## Model Details

| Field | Value |
|---|---|
| Backbone | EVA02-L/14 (MIM-22K) ([timm/eva02_large_patch14_224.mim_in22k](https://huggingface.co/timm/eva02_large_patch14_224.mim_in22k)) |
| Parameters | 303,286,225 |
| Input Resolution | RGB, 224x224 |
| Normalization | mean=(0.4815, 0.4578, 0.4082), std=(0.2686, 0.2613, 0.2758) |
| Output Targets | race (7 classes) + gender (2 classes) + age (8 ordinal thresholds / 9 brackets) |
| Test Set | 10,931 images (frozen deduplicated FairFace official validation set) |

## Training Data

Trained on the [HuggingFaceM4/FairFace](https://huggingface.co/datasets/HuggingFaceM4/FairFace) dataset (Karkkainen & Joo, WACV 2021; 97,698 raw images).

Deduplicated by content (SHA-256) for this project:
- **Train**: 77,926 images
- **Selection (val)**: 8,659 images
- **Test**: 10,931 images

All pairwise set intersections are zero; 0 images from the official training partition entered the evaluation set.

## Evaluation Results

| Task | Accuracy | Macro-F1 | Support |
|---|---:|---:|---:|
| Race (7 classes) | 77.02% | 76.83% | 10,931 |
| Gender (2 classes) | 96.87% | 96.86% | 10,931 |
| Age (9 ordinal brackets) | 63.93% | 61.29% | 10,931 |

3-Task Average Accuracy: **79.27%**. Age MAE: **0.3838 brackets**, +/-1 bracket accuracy: **97.94%**.

## Per-Class Performance

![per-class recall](assets/per_class_recall.png)

![confusion matrix](assets/confusion_matrix.png)

## Usage

```python
import inference

model = inference.load("model.pt")
predictions = inference.predict(model, "face.jpg")
print(predictions)
```

Dependencies: `torch`, `timm`, `torchvision`, `pillow`.

## Limitations & Ethical Considerations

- **Research Use Only**: This model is developed strictly for face attribute research, algorithmic bias measurement, and fairness auditing. **It must NOT be used for surveillance, identity verification, recruitment, credit evaluation, or any high-risk automated decision-making.**
- **Evaluation Set Reuse**: This frozen test set was evaluated across iterative checkpoints during development; reported metrics are descriptive.
- **Single Random Seed**: Training was conducted under a single seed; performance deltas under 0.3 pp should be considered statistical noise.
- **Demographic Disparities**: Demographic boundaries (notably between Latino/Hispanic, Middle Eastern, Indian, and White groups) are non-discrete; age estimation exhibits higher error rates, and specific intersectional gender x race subgroups show higher disparities.
- **Label Attribution**: Labels reflect the categorical annotations of the FairFace dataset and do not represent individual personal self-identification or genuine heritage.

## Data & Licensing

- **Dataset**: [HuggingFaceM4/FairFace](https://huggingface.co/datasets/HuggingFaceM4/FairFace), CC BY 4.0 (images sourced from YFCC100M under respective licenses).
- **Model Checkpoint**: Derivative work trained on FairFace, released under CC BY 4.0.
- **Pretrained Backbone**: [timm/eva02_large_patch14_224.mim_in22k](https://huggingface.co/timm/eva02_large_patch14_224.mim_in22k) (Apache-2.0).

## Citation

```bibtex
@inproceedings{karkkainen2021fairface,
  title={FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation},
  author={Karkkainen, Kimmo and Joo, Jungseock},
  booktitle={WACV},
  year={2021}
}
```