4 papers
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
Leonardo Santiago Benitez Pereira, Marcos Escudero Viñolo, Luis Herranz Arribas
Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearn…
SPARE: Self-distillation for PARameter-Efficient Removal
Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch +2
Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data pr…
Comparison of Information Retrieval Techniques Applied to IT Support Tickets
Leonardo Santiago Benitez Pereira, Robinson Pizzio, Samir Bonho
Institutions dependent on IT services and resources acknowledge the crucial significance of an IT help desk system, that act as a centralized hub connecting IT staff and users for…
PAT++: a cautionary tale about generative visual augmentation for Object Re-identification
Leonardo Santiago Benitez Pereira, Arathy Jeevan
Generative data augmentation has demonstrated gains in several vision tasks, but its impact on object re-identification - where preserving fine-grained visual details is essential…