Harnessing Unlabeled Data to Improve Generalization of Biometric Gender and Age Classifiers

10/09/2021
by   Aakash Varma Nadimpalli, et al.
0

With significant advances in deep learning, many computer vision applications have reached the inflection point. However, these deep learning models need large amount of labeled data for model training and optimum parameter estimation. Limited labeled data for model training results in over-fitting and impacts their generalization performance. However, the collection and annotation of large amount of data is a very time consuming and expensive operation. Further, due to privacy and security concerns, the large amount of labeled data could not be collected for certain applications such as those involving medical field. Self-training, Co-training, and Self-ensemble methods are three types of semi-supervised learning methods that can be used to exploit unlabeled data. In this paper, we propose self-ensemble based deep learning model that along with limited labeled data, harness unlabeled data for improving the generalization performance. We evaluated the proposed self-ensemble based deep-learning model for soft-biometric gender and age classification. Experimental evaluation on CelebA and VISOB datasets suggest gender classification accuracy of 94.46 1000 labeled samples and remaining 199k samples as unlabeled samples for CelebA dataset and similarly,1000 labeled samples with remaining 107k samples as unlabeled samples for VISOB dataset. Comparative evaluation suggest that there is 5.74% and 8.47% improvement in the accuracy of the self-ensemble model when compared with supervised model trained on the entire CelebA and VISOB dataset, respectively. We also evaluated the proposed learning method for age-group prediction on Adience dataset and it outperformed the baseline supervised deep-learning learning model with a better exact accuracy of 55.55 ± 4.28 which is 3.92

READ FULL TEXT

page 1

page 4

research
07/04/2022

Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools

Prediction of Remaining Useful Lifetime(RUL) in the modern manufacturing...
research
04/08/2021

Robust Self-Ensembling Network for Hyperspectral Image Classification

Recent research has shown the great potential of deep learning algorithm...
research
05/19/2023

Productive Crop Field Detection: A New Dataset and Deep Learning Benchmark Results

In precision agriculture, detecting productive crop fields is an essenti...
research
11/04/2021

Building Damage Mapping with Self-PositiveUnlabeled Learning

Humanitarian organizations must have fast and reliable data to respond t...
research
11/30/2017

Hybrid VAE: Improving Deep Generative Models using Partial Observations

Deep neural network models trained on large labeled datasets are the sta...
research
01/30/2019

Learning Fast Matching Models from Weak Annotations

This paper proposes a novel training scheme for fast matching models in ...

Please sign up or login with your details

Forgot password? Click here to reset