SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916230018891776 |
|---|---|
| author | Nakashima, Yuto Yang, Mingzhe Baba, Yukino |
| author_facet | Nakashima, Yuto Yang, Mingzhe Baba, Yukino |
| contents | Generating preferred images using generative adversarial networks (GANs) is challenging owing to the high-dimensional nature of latent space. In this study, we propose a novel approach that uses simple user-swipe interactions to generate preferred images for users. To effectively explore the latent space with only swipe interactions, we apply principal component analysis to the latent space of the StyleGAN, creating meaningful subspaces. We use a multi-armed bandit algorithm to decide the dimensions to explore, focusing on the preferences of the user. Experiments show that our method is more efficient in generating preferred images than the baseline methods. Furthermore, changes in preferred images during image generation or the display of entirely different image styles were observed to provide new inspirations, subsequently altering user preferences. This highlights the dynamic nature of user preferences, which our proposed approach recognizes and enhances. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19693 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration Nakashima, Yuto Yang, Mingzhe Baba, Yukino Human-Computer Interaction Computer Vision and Pattern Recognition Generating preferred images using generative adversarial networks (GANs) is challenging owing to the high-dimensional nature of latent space. In this study, we propose a novel approach that uses simple user-swipe interactions to generate preferred images for users. To effectively explore the latent space with only swipe interactions, we apply principal component analysis to the latent space of the StyleGAN, creating meaningful subspaces. We use a multi-armed bandit algorithm to decide the dimensions to explore, focusing on the preferences of the user. Experiments show that our method is more efficient in generating preferred images than the baseline methods. Furthermore, changes in preferred images during image generation or the display of entirely different image styles were observed to provide new inspirations, subsequently altering user preferences. This highlights the dynamic nature of user preferences, which our proposed approach recognizes and enhances. |
| title | SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.19693 |