Facial Attribute Classification
11 papers with code • 6 benchmarks • 9 datasets
Facial attribute classification is the task of classifying various attributes of a facial image - e.g. whether someone has a beard, is wearing a hat, and so on.
( Image credit: Multi-task Learning of Cascaded CNN for Facial Attribute Classification )
Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased.
In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced training data.
Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness.
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.
Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.
Two annotators independently assigning attribute values shows that only 12 of 40 common attributes are assigned values with >= 95% consistency, and three (high cheekbones, pointed nose, oval face) have essentially random consistency.
This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS).
Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded.