4 papers
Domain Generalization using Action Sequences for Egocentric Action Recognition
Amirshayan Nasirimajd, Chiara Plizzari, Simone Alberto Peirone +3
Recognizing human activities from visual inputs, particularly through a first-person viewpoint, is essential for enabling robots to replicate human behavior. Egocentric vision, cha…
Efficient Model Editing with Task-Localized Sparse Fine-tuning
Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network…
Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning
Leonardo Iurada, Marco Ciccone, Tatiana Tommasi
Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on th…
PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Niccolò Cavagnero, Gabriele Rosi, Claudia Cuttano +4
Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility, they obtain outstanding performance in multipl…