LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection
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_ | 1866917673862955008 |
|---|---|
| author | Nguyen, Dat Mejri, Nesryne Singh, Inder Pal Kuleshova, Polina Astrid, Marcella Kacem, Anis Ghorbel, Enjie Aouada, Djamila |
| author_facet | Nguyen, Dat Mejri, Nesryne Singh, Inder Pal Kuleshova, Polina Astrid, Marcella Kacem, Anis Ghorbel, Enjie Aouada, Djamila |
| contents | This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few small artifact-prone vulnerable regions. Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy. Experiments performed on several benchmarks show the superiority of our approach in terms of Area Under the Curve (AUC) and Average Precision (AP). The code is available at https://github.com/10Ring/LAA-Net. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13856 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection Nguyen, Dat Mejri, Nesryne Singh, Inder Pal Kuleshova, Polina Astrid, Marcella Kacem, Anis Ghorbel, Enjie Aouada, Djamila Computer Vision and Pattern Recognition This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few small artifact-prone vulnerable regions. Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy. Experiments performed on several benchmarks show the superiority of our approach in terms of Area Under the Curve (AUC) and Average Precision (AP). The code is available at https://github.com/10Ring/LAA-Net. |
| title | LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.13856 |