Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/134967
Título: When machine unlearning meets script identification
Autores/as: Souhaila Djaffal
Yasmina Benmabrouk
Chawki Djeddi
Díaz Cabrera, Moisés 
Nadhir Nouioua
Clasificación UNESCO: 3399 Otras especialidades tecnológicas (especificar)
Palabras clave: Computer vision
Image processing
Fecha de publicación: 2024
Conferencia: Irish Machine Vision and Image Processing Conference (26. Limerick. 2024)
Resumen: Machine Unlearning (MU) has emerged as a new paradigm for forgetting data samples from a given model. However, existing MU methods have focused on popular classification problems, leaving the landscape of unlearning for script identification and document analysis relatively unexplored. This paper addresses this gap by proposing an MU framework for script identification in scene text scenarios, utilizing deep learning networks. We conducted extensive experiments to assess the impact of data removal on different combinations of classes, including single and multiple classes, along with varying percentages of the forget set. We implemented two unlearning strategies: retraining from scratch (US) and fine-tuning (UF) for efficient forgetting manipulation. We evaluated our approach using a tiny vision transformer variant and ConvNeXt pre-trained models for scene text script identification on the SIW-13 dataset. Our results demonstrate that fine-tuning minimizes performance degradation.
URI: http://hdl.handle.net/10553/134967
DOI: https://doi.org/10.1049/icp.2024.3330
Fuente: 26th Irish Machine Vision and Image Processing Conference (IMVIP 2024)
Colección:Actas de congresos
Adobe PDF (146,69 kB)
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.