Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Facial Attribute Classification

3260 papers • 126 benchmarks • 313 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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in facial-attribute-classification

Trend

Dataset

Best Model

Actions

LFWA

LFWA

bFFHQ

bFFHQ

FairFace

FairFace

Libraries

i

Use these libraries to find facial-attribute-classification models and implementations

Datasets

UTKFace

MORPH

FairFace

LFWA

bFFHQ

CelebV-HQ

Subtasks

No subtasks available.

Most implemented papers

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

Jungseock Joo, Kimmo Kärkkäinen•Tue Aug 13 2019

A novel face image dataset is constructed, containing 108,501 images, with an emphasis of balanced race composition in the dataset, and it is found that the model trained from the dataset is substantially more accurate on novel datasets and the accuracy is consistent between race and gender groups.

186

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

UTKFace

UTKFace

DiveFace

DiveFace

MORPH

MORPH

CelebV-HQ

CelebV-HQ

DiveFace

DiveFace

IMDB-Clean

LAOFIW Dataset

A View From Somewhere (AVFS)

A View From Somewhere (AVFS)

0

Deep Learning Face Attributes in the Wild

Ziwei Liu, Ping Luo, Xiaogang Wang, Xiaoou Tang•Wed Nov 26 2014

A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.

9097 0

Learning from Failure: Training Debiased Classifier from Biased Classifier

Jinwoo Shin, J. Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee•Sun Jul 05 2020

This work intentionally train the first network to be biased by repeatedly amplifying its ''prejudice'', and debias the training of the second network by focusing on samples that go against the prejudice of the biased network in (a).

168 0

A novel batch-effect correction method for scRNA-seq data based on Adversarial Information Factorization

Lily Monnier, P. Cournède•Wed Jan 31 2024

Adversarial Information Factorization provides a robust batch-effect correction method that does not rely on prior knowledge of the cell types nor a specific normalization strategy while being adapted to any downstream analysis task, and best preserves the relative gene expression between cell types, yielding superior differential expression analysis results.

8 0

Imbalanced Deep Learning by Minority Class Incremental Rectification

Xiatian Zhu, S. Gong, Qi Dong•Fri Apr 27 2018

These experimental results demonstrate the performance advantages and model scalability of the proposed batch-wise incremental minority class rectification model over the existing state-of-the-art models for addressing the problem of imbalanced data learning.

352 0

Fair Contrastive Learning for Facial Attribute Classification

Pilhyeon Lee, H. Byun, Sungho Park, Jewook Lee, Sunhee Hwang, D. Kim•Tue Mar 29 2022

This paper analyzes unfairness caused by supervised contrastive learning and proposes a new Fair Supervised Contrastive Loss (FSCL) for fair visual representation learning, which significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-l accuracy and fairness.

111 0

Label2Label: A Language Modeling Framework for Multi-Attribute Learning

Jiwen Lu, Zhexuan Cao, Jianjiang Feng, Jie Zhou, Wanhua Li•Sun Jul 17 2022

Inspired by the remarkable success of pre-training language models in NLP, Label2Label introduces an image-conditioned masked language model, which randomly masks some of the"word"tokens from the label"sentence"and aims to recover them based on the masked"sentENCE"and the context conveyed by image features.

43 0

Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

Zhiheng Li, Chenliang Xu, A. Hoogs•Tue Jul 19 2022

This work proposes Debiasing Alternate Networks (DebiAN), which comprises two networks -- a Discoverer and a Classifier, and conducts 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.

65 0

Training Debiased Subnetworks with Contrastive Weight Pruning

Jong-Chul Ye, Geon Yeong Park, Sangmin Lee, Sang Wan Lee•Mon Oct 10 2022

A Debiased Contrastive Weight Pruning algorithm is proposed, which probes unbiased subnetworks without expensive group annotations and elucidates the importance of bias-conflicting samples on structure learning.

18 0

PANDA: Pose Aligned Networks for Deep Attribute Modeling

Marc'Aurelio Ranzato, Trevor Darrell, Lubomir D. Bourdev, Manohar Paluri, Ning Zhang•Wed Nov 20 2013

A new method which combines part-based models and deep learning by training pose-normalized CNNs for inferring human attributes from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion is proposed.

542 0

Adding a benchmark result helps the community track progress.

Facial Attribute Classification | State-of-the-Art