ArtBrain: An Explainable end-to-end Toolkit for Classification and Attribution of AI-Generated Art and Style
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_ | 1866910724384620544 |
|---|---|
| author | Silva, Ravidu Suien Rammuni Lotfi, Ahmad Ihianle, Isibor Kennedy Shahtahmassebi, Golnaz Bird, Jordan J. |
| author_facet | Silva, Ravidu Suien Rammuni Lotfi, Ahmad Ihianle, Isibor Kennedy Shahtahmassebi, Golnaz Bird, Jordan J. |
| contents | Recently, the quality of artworks generated using Artificial Intelligence (AI) has increased significantly, resulting in growing difficulties in detecting synthetic artworks. However, limited studies have been conducted on identifying the authenticity of synthetic artworks and their source. This paper introduces AI-ArtBench, a dataset featuring 185,015 artistic images across 10 art styles. It includes 125,015 AI-generated images and 60,000 pieces of human-created artwork. This paper also outlines a method to accurately detect AI-generated images and trace them to their source model. This work proposes a novel Convolutional Neural Network model based on the ConvNeXt model called AttentionConvNeXt. AttentionConvNeXt was implemented and trained to differentiate between the source of the artwork and its style with an F1-Score of 0.869. The accuracy of attribution to the generative model reaches 0.999. To combine the scientific contributions arising from this study, a web-based application named ArtBrain was developed to enable both technical and non-technical users to interact with the model. Finally, this study presents the results of an Artistic Turing Test conducted with 50 participants. The findings reveal that humans could identify AI-generated images with an accuracy of approximately 58%, while the model itself achieved a significantly higher accuracy of around 99%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01512 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ArtBrain: An Explainable end-to-end Toolkit for Classification and Attribution of AI-Generated Art and Style Silva, Ravidu Suien Rammuni Lotfi, Ahmad Ihianle, Isibor Kennedy Shahtahmassebi, Golnaz Bird, Jordan J. Artificial Intelligence Computer Vision and Pattern Recognition Recently, the quality of artworks generated using Artificial Intelligence (AI) has increased significantly, resulting in growing difficulties in detecting synthetic artworks. However, limited studies have been conducted on identifying the authenticity of synthetic artworks and their source. This paper introduces AI-ArtBench, a dataset featuring 185,015 artistic images across 10 art styles. It includes 125,015 AI-generated images and 60,000 pieces of human-created artwork. This paper also outlines a method to accurately detect AI-generated images and trace them to their source model. This work proposes a novel Convolutional Neural Network model based on the ConvNeXt model called AttentionConvNeXt. AttentionConvNeXt was implemented and trained to differentiate between the source of the artwork and its style with an F1-Score of 0.869. The accuracy of attribution to the generative model reaches 0.999. To combine the scientific contributions arising from this study, a web-based application named ArtBrain was developed to enable both technical and non-technical users to interact with the model. Finally, this study presents the results of an Artistic Turing Test conducted with 50 participants. The findings reveal that humans could identify AI-generated images with an accuracy of approximately 58%, while the model itself achieved a significantly higher accuracy of around 99%. |
| title | ArtBrain: An Explainable end-to-end Toolkit for Classification and Attribution of AI-Generated Art and Style |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.01512 |