Robust Data Augmentation Generative Adversarial Network for Object Detection
Generative adversarial network (GAN)-based data augmentation is used to enhance the performance of object detection models. It comprises two stages: training the GAN generator to learn the distribution of a small target dataset, and sampling data from the trained generator to enhance model performan...
Main Authors: | Hyungtak Lee, Seongju Kang, Kwangsue Chung |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/1/157 |
Similar Items
-
Image Generation with Global Photographic Aesthetic Based on Disentangled Generative Adversarial Network
by: Hua Zhang, et al.
Published: (2023-11-01) -
Correlation-Concealing Adversarial Noise Injection for Improved Disentanglement in Label-Based Image Translation
by: Seonguk Park, et al.
Published: (2023-01-01) -
Generative Adversarial Network for Class-Conditional Data Augmentation
by: Jeongmin Lee, et al.
Published: (2020-11-01) -
A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks
by: Efstathios Branikas, et al.
Published: (2023-01-01) -
Image-to-Image Translation-Based Structural Damage Data Augmentation for Infrastructure Inspection Using Unmanned Aerial Vehicle
by: Gi-Hun Gwon, et al.
Published: (2023-11-01)