Zeno Sambugaro — accepted AI-conference papers

2024

Lagrangian Hashing for Compressed Neural Field Representations

Shrisudhan Govindarajan*, Zeno Sambugaro, Akhmedkhan Shabanov, Towaki Takikawa, Weiwei Sun, Daniel Rebain +3

ECCV 2024poster

"We present Lagrangian Hashing, a representation for neural fields combining the characteristics of fast training NeRF methods that rely on Eulerian grids (i.e. InstantNGP), with those that employ points equipped with features as a way to represent information (e.g. 3D Gaussian Splatting or PointNeR…

Cited by 1 Source ↗PDF ↗Scholar ↗

2022

Interpretable Part-Whole Hierarchies and Conceptual-Semantic Relationships in Neural Networks

Nicola Garau, Niccolò Bisagno, Zeno Sambugaro, Nicola Conci

CVPR 2022oral

Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the hu…

Cited by 31 PDF ↗code ↗Scholar ↗

2021

Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces

Alireza Zaeemzadeh, Niccolo Bisagno, Zeno Sambugaro, Nicola Conci, Nazanin Rahnavard, Mubarak Shah

CVPR 2021poster

The goal of out-of-distribution (OOD) detection is to handle the situations where the test samples are drawn from a different distribution than the training data. In this paper, we argue that OOD samples can be detected more easily if the training data is embedded into a low-dimensional space, such…

Cited by 102 PDF ↗code ↗Scholar ↗