29 citations · 33 across the 12 of their papers we have counts for
13 papers
LVMT: Video Mask Transformer for Long-term Video Segmentation
Narges Norouzi, Niccol`o Cavagnero, Niccolò Cavagnero +4
Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusions. We hypothesize that this limitation is caused by (i) the ina…
Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
Svetlana Orlova, Niccolò Cavagnero, Gijs Dubbelman
Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in sub…
Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
Jing Gu, Niccolò Cavagnero, Gijs Dubbelman
Leveraging the general world knowledge of Large Language Models (LLMs) holds significant promise for improving the ability of autonomous driving systems to handle rare and complex…
PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders
Niccolò Cavagnero, Narges Norouzi, Gijs Dubbelman +1
Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for imag…
VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
Narges Norouzi, Idil Esen Zulfikar, Niccolò Cavagnero +4
Existing online video segmentation models typically combine a per-frame segmenter with complex specialized tracking modules. While effective, these modules introduce significant ar…
Searching on a Budget: HW-NAS with 10 Latency Probes
Francesco Capuano, Gabriele Tiboni, Niccolò Cavagnero +1
Existing hardware-aware NAS (HW-NAS) methods typically assume access to precise information circa the target device, either via analytical approximations of the post-compilation la…
Your ViT is Secretly an Image Segmentation Model
Tommie Kerssies, Niccolò Cavagnero, Alexander Hermans +5
Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing method…
Transient Fault Tolerant Semantic Segmentation for Autonomous Driving
Leonardo Iurada, Niccolò Cavagnero, Fernando Fernandes Dos Santos +3
Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults. We address the latter by exa…
The revenge of BiSeNet: Efficient Multi-Task Image Segmentation
Gabriele Rosi, Claudia Cuttano, Niccolò Cavagnero +2
Recent advancements in image segmentation have focused on enhancing the efficiency of the models to meet the demands of real-time applications, especially on edge devices. However,…
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…
Entropic Score metric: Decoupling Topology and Size in Training-free NAS
Niccolò Cavagnero, Luca Robbiano, Francesca Pistilli +2
Neural Networks design is a complex and often daunting task, particularly for resource-constrained scenarios typical of mobile-sized models. Neural Architecture Search is a promisi…
FreeREA: Training-Free Evolution-based Architecture Search
Niccolò Cavagnero, Luca Robbiano, Barbara Caputo +1
In the last decade, most research in Machine Learning contributed to the improvement of existing models, with the aim of increasing the performance of neural networks for the solut…
Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead
Niccolò Cavagnero, Fernando Dos Santos, Marco Ciccone +3
Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving. However,…