Controllable Image Dataset Construction Using Conditionally Transformed Inputs in Generative Adversarial Networks
In this paper, we tackle the well-known problem of dataset construction from the point of its generation using generative adversarial networks (GAN). As semantic information of the dataset should have a proper alignment with images, controlling the image generation process of GAN comes to the first...
Main Authors: | Farkhod Makhmudkhujaev, Junseok Kwon, In Kyu Park |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9585485/ |
Similar Items
-
Generative Adversarial Networks With Attention Mechanisms at Every Scale
by: Farkhod Makhmudkhujaev, et al.
Published: (2021-01-01) -
Universal Adversarial Training Using Auxiliary Conditional Generative Model-Based Adversarial Attack Generation
by: Hiskias Dingeto, et al.
Published: (2023-07-01) -
Conditional Generative Adversarial Network-Based Image Denoising for Defending Against Adversarial Attack
by: Haibo Zhang, et al.
Published: (2021-01-01) -
Long‐term scenario generation of renewable energy generation using attention‐based conditional generative adversarial networks
by: Hui Li, et al.
Published: (2024-02-01) -
Versatile Auxiliary Classification and Regression With Generative Adversarial Networks
by: Shabab Bazrafkan, et al.
Published: (2021-01-01)