1

AI-Assisted Diagnosis for Covid-19 CXR Screening: From Data Collection to Clinical Validation
n this paper, we present the major results from the Covid Radiographic imaging System based on AI (Co.R.S.A.) project, which took place …
PDF Cite Code Poster
A Differentiable Entropy Model for Learned Image Compression
n an end-to-end learned image compression framework, an encoder projects the image on a low-dimensional, quantized, latent space while …
PDF Cite
Two is Better than One: Achieving High-Quality 3D Scene Modeling with a NeRF Ensemble
Neural Radiance Field (NeRF) is a popular method for synthesizing novel views of a scene from a set of input images. While NeRF has …
PDF Cite Code Poster
Shannon Strikes Again! Entropy-based Pruning in Deep Neural Networks for Transfer Learning under Extreme Memory and Computation Budgets
Deep neural networks have become the de-facto standard across various computer science domains. Nonetheless, effectively training these …
Contrastive learning for regression in multi-site brain age prediction
Building accurate Deep Learning (DL) models for brain age prediction is a very relevant topic in neuroimaging, as it could help better …
PDF Cite Code Poster
Unbiased Supervised Contrastive Learning
Many datasets are biased, namely they contain easy-to-learn features that are highly correlated with the target class only in the …
PDF Cite Code Poster Slides Video
Unbiased Supervised Contrastive Learning
A Two-Step Radiologist-Like Approach for Covid-19 Computer-Aided Diagnosis from Chest X-Ray Images
Thanks to the rapid increase in computational capability during the latest years, traditional and more explainable methods have been …
PDF Cite Poster
Efficient Inference Of Image-Based Neural Network Models In Reconfigurable Systems With Pruning And Quantization
Neural networks (NN) for image processing in embedded systems expose two conflicting requirements: increasing computing power needs as …
PDF Cite
Lung Nodules Segmentation with DeepHealth Toolkit
The accurate and consistent border segmentation plays an important role in the tumor volume estimation and its treatment in the field …
PDF Cite
To update or not to update? Neurons at equilibrium in deep models
Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible …
PDF Cite Poster