8 citations · 11 across the 23 of their papers we have counts for
25 papers
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed +2
Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable…
Cardiac Output Prediction from Echocardiograms: Self-Supervised Learning with Limited Data
Adson Duarte, Davide Vitturini, Emanuele Milillo +9
Cardiac Output (CO) is a key parameter in the diagnosis and management of cardiovascular diseases. However, its accurate measurement requires right-heart catheterization, an invasi…
Synthetic Dataset Generation and Validation for Robotic Surgery Instrument Segmentation
Giorgio Chiesa, Rossella Borra, Vittorio Lauro +5
This paper presents a comprehensive workflow for generating and validating a synthetic dataset designed for robotic surgery instrument segmentation. A 3D reconstruction of the Da V…
Automated Prediction of Paravalvular Regurgitation before Transcatheter Aortic Valve Implantation
Michele Cannito, Riccardo Renzulli, Adson Duarte +9
Severe aortic stenosis is a common and life-threatening condition in elderly patients, often treated with Transcatheter Aortic Valve Implantation (TAVI). Despite procedural advance…
Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere
Francesco Di Sario, Daniel Rebain, Dor Verbin +2
Radiance field methods (e.g. 3D Gaussian Splatting) have emerged as a powerful paradigm for novel view synthesis, yet their appearance modeling often relies on Spherical Harmonics…
MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
Riccardo Renzulli, Colas Lepoutre, Enrico Cassano +1
Artificial intelligence in healthcare requires models that are accurate and interpretable. We advance mechanistic interpretability in medical vision by applying Medical Sparse Auto…
SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
Enrico Cassano, Riccardo Renzulli, Marco Nurisso +3
Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computatio…
When Does Pruning Benefit Vision Representations?
Enrico Cassano, Riccardo Renzulli, Andrea Bragagnolo +1
Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper invest…
Neural Velocity for hyperparameter tuning
Gianluca Dalmasso, Andrea Bragagnolo, Enzo Tartaglione +2
Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training a…
Robust brain age estimation from structural MRI with contrastive learning
Carlo Alberto Barbano, Benoit Dufumier, Edouard Duchesnay +2
Estimating brain age from structural MRI has emerged as a powerful tool for characterizing normative and pathological aging. In this work, we explore contrastive learning as a scal…
Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo +5
Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, re…
GoDe: Gaussians on Demand for Backbone-Agnostic Progressive Compression
Francesco Di Sario, Riccardo Renzulli, Marco Grangetto +2
Splat-based radiance fields have rapidly diversified in primitive type, kernel support, and appearance parameterization. This diversity makes compression difficult: most codecs are…
AA-SGAN: Adversarially Augmented Social GAN with Synthetic Data
Mirko Zaffaroni, Federico Signoretta, Marco Grangetto +1
Accurately predicting pedestrian trajectories is crucial in applications such as autonomous driving or service robotics, to name a few. Deep generative models achieve top performan…
If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions
Carlo Alberto Barbano, Luca Molinaro, Massimiliano Ciranni +3
Humans can visualize new and unknown concepts from their natural language description, based on their experience and previous knowledge. Insipired by this, we present a way to exte…
Efficient Progressive Image Compression with Variance-aware Masking
Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti +2
Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compre…
STanH : Parametric Quantization for Variable Rate Learned Image Compression
Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti +1
In end-to-end learned image compression, encoder and decoder are jointly trained to minimize a cost function, where controls the trade-off between rate of the quantize…
GABIC: Graph-based Attention Block for Image Compression
Gabriele Spadaro, Alberto Presta, Enzo Tartaglione +3
While standardized codecs like JPEG and HEVC-intra represent the industry standard in image compression, neural Learned Image Compression (LIC) codecs represent a promising alterna…
WiGNet: Windowed Vision Graph Neural Network
Gabriele Spadaro, Marco Grangetto, Attilio Fiandrotti +2
In recent years, Graph Neural Networks (GNNs) have demonstrated strong adaptability to various real-world challenges, with architectures such as Vision GNN (ViG) achieving state-of…
Anatomical Foundation Models for Brain MRIs
Carlo Alberto Barbano, Matteo Brunello, Benoit Dufumier +1
Deep Learning (DL) in neuroimaging has become increasingly relevant for detecting neurological conditions and neurodegenerative disorders. One of the most predominant biomarkers in…
Boost Your NeRF: A Model-Agnostic Mixture of Experts Framework for High Quality and Efficient Rendering
Francesco Di Sario, Riccardo Renzulli, Enzo Tartaglione +1
Since the introduction of NeRFs, considerable attention has been focused on improving their training and inference times, leading to the development of Fast-NeRFs models. Despite d…
Multi-target stain normalization for histology slides
Desislav Ivanov, Carlo Alberto Barbano, Marco Grangetto
Traditional staining normalization approaches, e.g. Macenko, typically rely on the choice of a single representative reference image, which may not adequately account for the diver…
Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion models
Cristiano Patrício, Carlo Alberto Barbano, Attilio Fiandrotti +4
Contrastive Analysis (CA) detects anomalies by contrasting patterns unique to a target group (e.g., unhealthy subjects) from those in a background group (e.g., healthy subjects). I…
AI-Assisted Diagnosis for Covid-19 CXR Screening: From Data Collection to Clinical Validation
Carlo Alberto Barbano, Riccardo Renzulli, Marco Grosso +3
In this paper, we present the major results from the Covid Radiographic imaging System based on AI (Co.R.S.A.) project, which took place in Italy. This project aims to develop a st…
Domain Adaptation for Learned Image Compression with Supervised Adapters
Alberto Presta, Gabriele Spadaro, Enzo Tartaglione +2
In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on natural images; yet i…