Age and gender classification using convolutional neural networks

By Gil Levi, Tal Hassner. 2015

1,157 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Women also Snowboard: Overcoming Bias in Captioning Models (2018, background): “Gender classification models frequently focus on facial features [38,39,40].”
Quantized Convolutional Neural Networks for Mobile Devices (2015, background): “In recent years, we have witnessed the great success of convolutional neural networks (CNN) [19] in a wide range of visual applications, including image classification [16, 27], object detection [10, 9], age estimation [24, 23], etc.”
Recent advances in convolutional neural networks (2015, methodology): “Popular augmentation methods include simple geometric transformations such as sampling [7, 107], mirroring [106, 108], rotating [109], shifting [110], and various photometric transformations [111, 112].”
Diversity in Faces (2019, methodology): “Many other data sets have been proposed for different facial analysis tasks, such as age and gender classification [24, 27, 31, 54–56], facial expression analysis [55], memorability [57], attributes [35] and aging [58].”
Unmasking Clever Hans predictors and assessing what machines really learn (2019, background): “They have scored commanding successes in the venues of strategic games [5,7, 58,79], image classification [78], face [80,81] recognition, speech recognition [82] and e.”
Age Progression/Regression by Conditional Adversarial Autoencoder (2017, methodology): “The age and gender of the crawled faces are estimated based on the image caption or the result from age estimator [16].”
A systematic study of the class imbalance problem in convolutional neural networks (2017, methodology): “The most commonly used method in both classical machine learning and deep learning is oversampling [11, 35, 36, 37].”
Deep Multi-task Representation Learning: A Tensor Factorisation Approach (2016, methodology): “Two independent CNN models for this benchmark are introduced in [Levi and Hassncer, 2015].”
Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering (2016, background): “Over the last few years, a number of valuable datasets and models targeting specific tasks such as scene recognition [10], age, gender, and emotion classification [11,12], human action recognition [13,14,15], etc.”
Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns (2015, methodology): “In the related work of [21] oversampling was shown to provide superior age and gender classification performance on the Adience benchmark [13].”
Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning (2019, methodology): “Lee et al. [10] follow the study of [11] to build a lightweight CNN that can be deployed on mobile devices.”
Can you tell where in India I am from? Comparing humans and computers on fine-grained race face classification (2017, methodology): “We have used the VGG-Face [10] face recognition CNN which is has been fine tuned for face recognition, additionally we have also evaluated a CNN trained for age classification [7] and one for gender classification [7] and we refer to these models as CNNage and CNN-gender hereafter.”
Deep learning for magnification independent breast cancer histopathology image classification (2016, methodology): “Previously, it was used for age and gender estimation from real-world images [23].”
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics (2017, methodology): “Recently, deep convolutional neural networks have been used for this problem [27,38,41].”
Decoupling "when to update" from "how to update" (2017, methodology): “We use a network architecture suggested by [24], using an available tensorflow implementation 1 .”
AgeDB: The First Manually Collected, In-the-Wild Age Database (2017, background): “In 2014, AdienceFaces database [8, 25] was introduced, containing 26,580 “in-the-wild” images of 2,984 subjects.”