59 citations · 97 across the 12 of their papers we have counts for
13 papers
Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation
Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov +6
Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the execution cost. Despite its…
Accelerating Vision Foundation Models with Drop-in Depthwise Convolution
Carmelo Scribano, Mohammad Mahdi, Nedyalko Prisadnikov +5
Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs,…
Low-Latency Embedded Driver Monitoring System with a Multi-Task Neural Network
Carmelo Scribano, Giovanni Cappelletti, Elia Giacobazzi +3
Road traffic accidents remain a significant global concern, with the majority attributed to human factors such as driver distraction and fatigue. This study proposes a camera-based…
Segment Anything for Satellite Imagery: A Strong Baseline and a Regional Dataset for Automatic Field Delineation
Carmelo Scribano, Elena Govi, Paolo Bertellini +3
Accurate mapping of agricultural field boundaries is essential for the efficient operation of agriculture. Automatic extraction from high-resolution satellite imagery, supported by…
Majorization-Minimization for sparse SVMs
Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini +5
Several decades ago, Support Vector Machines (SVMs) were introduced for performing binary classification tasks, under a supervised framework. Nowadays, they often outperform other…
Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation
Elena Govi, Davide Sapienza, Carmelo Scribano +5
In recent years, there has been a growing trend of using data-driven methods in industrial settings. These kinds of methods often process video images or parts, therefore the integ…
Model-Based Underwater 6D Pose Estimation from RGB
Davide Sapienza, Elena Govi, Sara Aldhaheri +5
Object pose estimation underwater allows an autonomous system to perform tracking and intervention tasks. Nonetheless, underwater target pose estimation is remarkably challenging d…
Explainable bilevel optimization: an application to the Helsinki deblur challenge
Silvia Bonettini, Giorgia Franchini, Danilo Pezzi +1
In this paper we present a bilevel optimization scheme for the solution of a general image deblurring problem, in which a parametric variational-like approach is encapsulated withi…
CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning
Carmelo Scribano, Giorgia Franchini, Ignacio Sañudo Olmedo +1
Perceiving the surrounding environment is essential for enabling autonomous or assisted driving functionalities. Common tasks in this domain include detecting road users, as well a…
DCT-Former: Efficient Self-Attention with Discrete Cosine Transform
Carmelo Scribano, Giorgia Franchini, Marco Prato +1
Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications.…
All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers
Carmelo Scribano, Davide Sapienza, Giorgia Franchini +2
Combining Natural Language with Vision represents a unique and interesting challenge in the domain of Artificial Intelligence. The AI City Challenge Track 5 for Natural Language-Ba…
Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM
Pasquale Cascarano, Andrea Sebastiani, Maria Colomba Comes +2
In the last decades, unsupervised deep learning based methods have caught researchers attention, since in many real applications, such as medical imaging, collecting a great amount…
Mise en abyme with artificial intelligence: how to predict the accuracy of NN, applied to hyper-parameter tuning
Giorgia Franchini, Mathilde Galinier, Micaela Verucchi
In the context of deep learning, the costliest phase from a computational point of view is the full training of the learning algorithm. However, this process is to be used a signif…