Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.15778 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911216956342272 |
|---|---|
| author | Pavlov, Ilia |
| author_facet | Pavlov, Ilia |
| contents | As image generative models continue to increase not only in their fidelity but also in their ubiquity the development of tools that leverage direct interaction with their internal mechanisms in an interpretable way has received little attention In this work we introduce a system that allows users to develop a better understanding of the model through interaction and experimentation By giving users the ability to replace activation functions of a generative network with parametric ones and a way to set the parameters of these functions we introduce an alternative approach to control the networks output We demonstrate the use of our method on StyleGAN2 and BigGAN networks trained on FFHQ and ImageNet respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15778 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Controlling the image generation process with parametric activation functions Pavlov, Ilia Computer Vision and Pattern Recognition Artificial Intelligence As image generative models continue to increase not only in their fidelity but also in their ubiquity the development of tools that leverage direct interaction with their internal mechanisms in an interpretable way has received little attention In this work we introduce a system that allows users to develop a better understanding of the model through interaction and experimentation By giving users the ability to replace activation functions of a generative network with parametric ones and a way to set the parameters of these functions we introduce an alternative approach to control the networks output We demonstrate the use of our method on StyleGAN2 and BigGAN networks trained on FFHQ and ImageNet respectively. |
| title | Controlling the image generation process with parametric activation functions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.15778 |