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

Age And Gender Classification

3260 papers • 126 benchmarks • 313 datasets

Age and gender classification is a dual-task of identifying the age and gender of a person from an image or video. ( Image credit: Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in age-and-gender-classification

Trend

Dataset

Best Model

Actions

Adience Age

Adience Age

Adience Gender

Adience Gender

Libraries

i

Use these libraries to find age-and-gender-classification models and implementations

Datasets

CI-MNIST

IMDB-Clean

LAGENDA

Age and Gender

Subtasks

No subtasks available.

Most implemented papers

Rank consistent ordinal regression for neural networks with application to age estimation

S. Raschka, Wenzhi Cao, Vahid Mirjalili•Sat Jan 19 2019

The COnsistent RAnk Logits (CORAL) framework is proposed with strong theoretical guarantees for rank-monotonicity and consistent confidence scores and can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks.

274

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning

Chu-Song Chen, Steven C. Y. Hung, Jia-Hong Lee, Timmy S. T. Wan, Chien-Hung Chen, Yi-Ming Chan•Tue Jun 04 2019

The proposed packing-and-expanding method is effective and easy to implement, which can iteratively shrink and enlarge the model to integrate new functions and maintains the compactness in continual learning.

47 0

Quantifying Facial Age by Posterior of Age Comparisons

Chen Change Loy, Cheng Li, Yunxuan Zhang, Li Liu•Mon Jul 31 2017

This work introduces a novel approach for annotating large quantity of in-the-wild facial images with high-quality posterior age distribution as labels and trains a network that jointly performs ordinal hyperplane classification and posterior distribution learning.

83 0

A Fusion-based Gender Recognition Method Using Facial Images

H. Mohammadzade, Benyamin Ghojogh, S. Shouraki, Ensieh Iranmehr•Thu Nov 16 2017

This paper utilizes pre-processing and a landmark detection method in order to find the important landmarks of faces and takes advantage of both texture and geometrical information, the two dominant types of information in facial gender recognition.

14 0

Joint Estimation of Age and Gender from Unconstrained Face Images Using Lightweight Multi-Task CNN for Mobile Applications

Chu-Song Chen, Jia-Hong Lee, Yi-Ming Chan, Ting-Yen Chen•Tue Jun 05 2018

This paper presents an efficient convolutional neural network called lightweight multi-task CNN for simultaneous age and gender classification, which uses depthwise separable convolution to reduce the model size and save the inference time.

34 0

Multimodal Age and Gender Classification Using Ear and Profile Face Images

H. K. Ekenel, Dogucan Yaman, Fevziye Irem Eyiokur•Fri May 31 2019

This paper presents multimodal deep neural network frameworks for age and gender classification, which take input a profile face image as well as an ear image, to enhance the accuracy of soft biometric trait extraction from profile face images by additionally utilizing a promising biometric modality: ear appearance.

33 0

Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression

Jiwen Lu, Jie Zhou, Jianjiang Feng, Wanhua Li, Xiaoke Huang•Wed Mar 24 2021

Uncertainty is the only certainty there is. Modeling data uncertainty is essential for regression, especially in unconstrained settings. Traditionally the direct regression formulation is considered and the uncertainty is modeled by modifying the output space to a certain family of probabilistic distributions. On the other hand, classification based regression and ranking based solutions are more popular in practice while the direct regression methods suffer from the limited performance. How to model the uncertainty within the present-day technologies for regression remains an open issue. In this paper, we propose to learn probabilistic ordinal embeddings which represent each data as a multivariate Gaussian distribution rather than a deterministic point in the latent space. An ordinal distribution constraint is proposed to exploit the ordinal nature of regression. Our probabilistic ordinal embeddings can be integrated into popular regression approaches and empower them with the ability of uncertainty estimation. Experimental results show that our approach achieves competitive performance. Code is available at https://github.com/Li-Wanhua/POEs.

73 0

Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics

Soroush Mehri, Charan Reddy, Deepak Sharma, Adriana Romero-Soriano, Samira Shabanian, Sina Honari•Thu Dec 31 2020

The results show that the bias of models increase as datasets become more imbalanced or datasets attributes become more correlated, the level of dominance of correlated sensitive dataset features impact bias, and the sensitive information remains in the latent representation even when bias-mitigation algorithms are applied.

36 0

Compacting, Picking and Growing for Unforgetting Continual Learning

Chu-Song Chen, Steven C. Y. Hung, Chien-Hung Chen, Yi-Ming Chan, Cheng-Hao Tu, Cheng-En Wu•Mon Oct 14 2019

This paper introduces an incremental learning method that is scalable to the number of sequential tasks in a continual learning process and shows that the knowledge accumulated through learning previous tasks is helpful to build a better model for the new tasks compared to training the models independently with tasks.

354 0

Adding a benchmark result helps the community track progress.

Age And Gender Classification | State-of-the-Art