Facial Attribute Classification

16 papers with code • 7 benchmarks • 10 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 )

Most implemented papers

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age

joojs/fairface 14 Aug 2019

Images were collected from the YFCC-100M Flickr dataset and labeled with race, gender, and age groups.

Deep Learning Face Attributes in the Wild

facebookresearch/disentangling-correlated-factors ICCV 2015

LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction.

Learning from Failure: Training Debiased Classifier from Biased Classifier

alinlab/BAR 6 Jul 2020

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased.

PANDA: Pose Aligned Networks for Deep Attribute Modeling

FanjieLUO/matlab CVPR 2014

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion.

Adversarial Information Factorization

ToniCreswell/attribute-cVAEGAN ICLR 2019

We propose a novel generative model architecture designed to learn representations for images that factor out a single attribute from the rest of the representation.

Imbalanced Deep Learning by Minority Class Incremental Rectification

AemikaChow/DATASOURCE 28 Apr 2018

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.

Fair Contrastive Learning for Facial Attribute Classification

sungho-coolg/fscl CVPR 2022

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.

Label2Label: A Language Modeling Framework for Multi-Attribute Learning

li-wanhua/label2label 18 Jul 2022

As each sample is annotated with multiple attribute labels, these "words" will naturally form an unordered but meaningful "sentence", which depicts the semantic information of the corresponding sample.

Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

zhihengli-UR/DebiAN 20 Jul 2022

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.

Training Debiased Subnetworks with Contrastive Weight Pruning

parkgeonyeong/dcwp CVPR 2023

Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.