Automated In-the-Wild Data Collection for Continual AI Generated Image Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913086804328448 |
|---|---|
| author | Pantsios, Thanasis Karageorgiou, Dimitrios Koutlis, Christos Karantaidis, George Papadopoulou, Olga Papadopoulos, Symeon |
| author_facet | Pantsios, Thanasis Karageorgiou, Dimitrios Koutlis, Christos Karantaidis, George Papadopoulou, Olga Papadopoulos, Symeon |
| contents | The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and when encountering newly emerging generative models. In this work, we propose a data-centric continual adaptation framework for updating detectors in evolving environments. We show that both in-the-wild data and generator-driven data are essential for adapting detectors. We introduce an automated, weakly supervised pipeline for constructing in-the-wild datasets through fact-check article retrieval. Additionally, we demonstrate that incorporating even a small amount of generator-driven data during training enables effective adaptation to newly emerging models, while combining it with in-the-wild data within a continual learning framework enables robust adaptation and mitigates catastrophic forgetting. Extensive experiments on two state-of-the-art detectors show significant improvements of +9.14% and +8% in average accuracy, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02567 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Automated In-the-Wild Data Collection for Continual AI Generated Image Detection Pantsios, Thanasis Karageorgiou, Dimitrios Koutlis, Christos Karantaidis, George Papadopoulou, Olga Papadopoulos, Symeon Computer Vision and Pattern Recognition The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and when encountering newly emerging generative models. In this work, we propose a data-centric continual adaptation framework for updating detectors in evolving environments. We show that both in-the-wild data and generator-driven data are essential for adapting detectors. We introduce an automated, weakly supervised pipeline for constructing in-the-wild datasets through fact-check article retrieval. Additionally, we demonstrate that incorporating even a small amount of generator-driven data during training enables effective adaptation to newly emerging models, while combining it with in-the-wild data within a continual learning framework enables robust adaptation and mitigates catastrophic forgetting. Extensive experiments on two state-of-the-art detectors show significant improvements of +9.14% and +8% in average accuracy, respectively. |
| title | Automated In-the-Wild Data Collection for Continual AI Generated Image Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02567 |