scholarly journals Evaluating the Performance of a Large-Scale Facial Image Dataset Using Agglomerated Match Score Statistics

2016 ◽  
Author(s):  
Mounica Kamireddy
Keyword(s):  
Large Scale ◽  
Facial Image ◽  
Score Statistics ◽  
Image Dataset ◽  
Match Score

scholarly journals Large-scale geo-facial image analysis

2015 ◽  
Vol 2015 (1) ◽  
Author(s):  
Mohammad T. Islam ◽  
Connor Greenwell ◽  
Richard Souvenir ◽  
Nathan Jacobs
Keyword(s):  
Image Analysis ◽  
Large Scale ◽  
Facial Image ◽  
Facial Image Analysis

scholarly journals LSUN-Stanford Car Dataset: Enhancing Large-Scale Car Image Datasets Using Deep Learning for Usage in GAN Training

2020 ◽  
Vol 10 (14) ◽  
pp. 4913
Author(s):  
Tin Kramberger ◽  
Božidar Potočnik
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Large Scale ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Image Dataset ◽  
Image Datasets

Currently there is no publicly available adequate dataset that could be used for training Generative Adversarial Networks (GANs) on car images. All available car datasets differ in noise, pose, and zoom levels. Thus, the objective of this work was to create an improved car image dataset that would be better suited for GAN training. To improve the performance of the GAN, we coupled the LSUN and Stanford car datasets. A new merged dataset was then pruned in order to adjust zoom levels and reduce the noise of images. This process resulted in fewer images that could be used for training, with increased quality though. This pruned dataset was evaluated by training the StyleGAN with original settings. Pruning the combined LSUN and Stanford datasets resulted in 2,067,710 images of cars with less noise and more adjusted zoom levels. The training of the StyleGAN on the LSUN-Stanford car dataset proved to be superior to the training with just the LSUN dataset by 3.7% using the Fréchet Inception Distance (FID) as a metric. Results pointed out that the proposed LSUN-Stanford car dataset is more consistent and better suited for training GAN neural networks than other currently available large car datasets.

Sign in / Sign up

Export Citation Format

Share Document