A Convolutional Neural Network for Gender Recognition Optimizing the Accuracy/Speed Tradeoff

Abstract

Gender recognition has been among the most investigated problems in the last years; although several contributions have been proposed, gender recognition in unconstrained environments is still a challenging problem and a definitive solution has not been found yet. Furthermore, Deep Convolutional Neural Networks (DCNNs) achieve very interesting performance, but they typically require a huge amount of computational resources (CPU, GPU, RAM, storage), that are not always available in real systems, due to their cost or to specific application constraints (when the application needs to be installed directly on board of low-power smart cameras, e.g. for digital signage). In the latest years the Machine Learning community developed an interest towards optimizing the efficiency of Deep Learning solutions, in order to make them portable and widespread. In this work we propose a compact DCNN architecture for Gender Recognition from face images that achieves approximately state of the art accuracy at a highly reduced computational cost (almost five times). We also perform a sensitivity analysis in order to show how some changes in the architecture of the network can influence the tradeoff between accuracy and speed. In addition, we compare our optimized architecture with popular efficient CNNs on various common benchmark dataset, widely adopted in the scientific community, namely LFW, MIVIA-Gender, IMDB-WIKI and Adience, demonstrating the effectiveness of the proposed solution.

Effective training of convolutional neural networks for age estimation based on knowledge distillation

“…This procedure of testing without fine-tuning has been used on the same LFW? dataset in different tasks such as gender recognition [2,18]; it is called cross-dataset evaluation and allows to assess the generalizability of the features that can be learned through the training dataset. The evaluation metric we adopt for this dataset is the mean absolute error (MAE).…”

“…Although very effective, the methodologies based on convolutional neural networks are often slow and resource demanding. Efficient network architectures targeted at biometric analysis exist [18], but they often require a sacrifice in accuracy, while the most accurate methodologies can be extremely bulky and slow [2], namely unusable for practical applications despite their reliability.…”

A Lightweight Deep Convolutional Neural Network Model for Real-Time Age and Gender Prediction

“…In recent years, other researchers developed a Deep CNN architecture for gender detection with standard accuracy and low computational cost. They compared their architecture with other popular CNN with common datasets namely IMDB-WIKI, LFW, and Adience dataset [18]. In [19] they implemented a lightweight model for age and gender estimation.…”

Bagging ensemble for deep learning based gender recognition using test-time augmentation on large-scale datasets

“…Visual data can be a portrait face, 3D volume, gait, body, or even just hands [1] or ears [2]. Face based gender recognition under unconstrained settings is getting more attention in recent years [3][4][5]. It contributes to the other vision problems and research fields such as biometrics, face recognition, age prediction, targeted advertising, recommendation systems, and human-computer interaction.…”