BAGAN: Effective Data Generation Based on GAN Augmented 3D Synthesizing

Augment reality (AR) is crucial for immersive human-computer interaction (HCI) and vision of artificial intelligence (AI). Labeled data drove object recognition in AR. However, manual annotating data is expensive and labor-intensive, and furthermore, scanty labeled data limits the application of AR. Aiming at solving the problem of insufficient training data in AR object recognition, an automated vision data synthesis method called BAGAN is proposed in this paper based on the 3D modeling and GAN algorithm. Our approach has been validated to have better performance than other methods through image recognition task on natural image database ObjectNet3D. This study can shorten the algorithm development time of AR and expand the application scope of AR, which is of great significance to immersive interactive systems.

Download Full-text

Background Augmentation Generative Adversarial Networks (BAGANs): Effective Data Generation Based on GAN-Augmented 3D Synthesizing

Symmetry ◽

10.3390/sym10120734 ◽

2018 ◽

Vol 10 (12) ◽

pp. 734 ◽

Cited By ~ 5

Author(s):

Yan Ma ◽

Kang Liu ◽

Zhibin Guan ◽

Xinkai Xu ◽

Xu Qian ◽

...

Keyword(s):

Object Recognition ◽

Synthesis Method ◽

Interactive Systems ◽

Training Data ◽

Generative Adversarial Networks ◽

Natural Image ◽

Data Generation ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Adversarial Networks

Augmented Reality (AR) is crucial for immersive Human–Computer Interaction (HCI) and the vision of Artificial Intelligence (AI). Labeled data drives object recognition in AR. However, manually annotating data is expensive, labor-intensive, and data distribution asymmetry . Scantily labeled data limits the application of AR. Aiming at solving the problem of insufficient and asymmetry training data in AR object recognition, an automated vision data synthesis method, i.e., background augmentation generative adversarial networks (BAGANs), is proposed in this paper based on 3D modeling and the Generative Adversarial Network (GAN) algorithm. Our approach has been validated to have better performance than other methods through image recognition tasks with respect to the natural image database ObjectNet3D. This study can shorten the algorithm development time of AR and expand its application scope, which is of great significance for immersive interactive systems.

Download Full-text

Use It and Still Lose It?

GeroPsych ◽

10.1024/1662-9647/a000020 ◽

2010 ◽

Vol 23 (3) ◽

pp. 169-175 ◽

Cited By ~ 14

Author(s):

Adrian Schwaninger ◽

Diana Hardmeier ◽

Judith Riegelnig ◽

Mike Martin

Keyword(s):

Object Recognition ◽

Cognitive Development ◽

Recognition Test ◽

Cognitive Aging ◽

Recognition Task ◽

Airport Security ◽

Visual Object ◽

Long Term Effects ◽

Object Recognition Test ◽

X Ray

In recent years, research on cognitive aging increasingly has focused on the cognitive development across middle adulthood. However, little is still known about the long-term effects of intensive job-specific training of fluid intellectual abilities. In this study we examined the effects of age- and job-specific practice of cognitive abilities on detection performance in airport security x-ray screening. In Experiment 1 (N = 308; 24–65 years), we examined performance in the X-ray Object Recognition Test (ORT), a speeded visual object recognition task in which participants have to find dangerous items in x-ray images of passenger bags; and in Experiment 2 (N = 155; 20–61 years) in an on-the-job object recognition test frequently used in baggage screening. Results from both experiments show high performance in older adults and significant negative age correlations that cannot be overcome by more years of job-specific experience. We discuss the implications of our findings for theories of lifespan cognitive development and training concepts.

Download Full-text

Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

Remote Sensing ◽

10.3390/rs13091713 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1713

Author(s):

Songwei Gu ◽

Rui Zhang ◽

Hongxia Luo ◽

Mengyao Li ◽

Huamei Feng ◽

...

Keyword(s):

Remote Sensing ◽

Real Life ◽

Attention Mechanism ◽

Training Data ◽

Generative Adversarial Networks ◽

Natural Image ◽

Remote Sensing Images ◽

Training Time ◽

Adversarial Networks ◽

Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

Download Full-text

Mice deficient in the NAAG synthetase II gene Rimkla are impaired in a novel object recognition task

Journal of Neurochemistry ◽

10.1111/jnc.15333 ◽

2021 ◽

Author(s):

Ivonne Becker ◽

Lihua Wang‐Eckhardt ◽

Julia Lodder‐Gadaczek ◽

Yong Wang ◽

Agathe Grünewald ◽

...

Keyword(s):

Object Recognition ◽

Recognition Task ◽

Novel Object Recognition ◽

Novel Object ◽

Object Recognition Task ◽

Novel Object Recognition Task

Download Full-text

Efficient Training Data Generation for Phase-Based DOA Estimation

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp39728.2021.9414070 ◽

2021 ◽

Author(s):

Fabian Hubner ◽

Wolfgang Mack ◽

Emanuel A. P. Habets

Keyword(s):

Doa Estimation ◽

Training Data ◽

Data Generation

Download Full-text

BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data

Sensors ◽

10.3390/s21062144 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2144

Author(s):

Stefan Reitmann ◽

Lorenzo Neumann ◽

Bernhard Jung

Keyword(s):

Point Clouds ◽

Training Data ◽

Sensor Data ◽

Generation Process ◽

Data Generation ◽

Depth Sensor ◽

Depth Sensing ◽

Depth Sensors ◽

3D Point Clouds ◽

Wide Range

Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the BLAINDER add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the BLAINDER add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.

Download Full-text