Search Results for author: Gabriele Valvano

Found 10 papers, 7 papers with code

Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning

1 code implementation26 Aug 2021 Gabriele Valvano, Andrea Leo, Sotirios A. Tsaftaris

Collecting large-scale medical datasets with fine-grained annotations is time-consuming and requires experts.

Weakly supervised segmentation

Measuring the Biases and Effectiveness of Content-Style Disentanglement

2 code implementations27 Aug 2020 Xiao Liu, Spyridon Thermos, Gabriele Valvano, Agisilaos Chartsias, Alison O'Neil, Sotirios A. Tsaftaris

In this paper, we conduct an empirical study to investigate the role of different biases in content-style disentanglement settings and unveil the relationship between the degree of disentanglement and task performance.

Disentanglement Image-to-Image Translation

Learning to Segment from Scribbles using Multi-scale Adversarial Attention Gates

3 code implementations2 Jul 2020 Gabriele Valvano, Andrea Leo, Sotirios A. Tsaftaris

We evaluated our model on several medical (ACDC, LVSC, CHAOS) and non-medical (PPSS) datasets, and we report performance levels matching those achieved by models trained with fully annotated segmentation masks.

Deep Attention Image Segmentation +4

Temporal Consistency Objectives Regularize the Learning of Disentangled Representations

1 code implementation29 Aug 2019 Gabriele Valvano, Agisilaos Chartsias, Andrea Leo, Sotirios A. Tsaftaris

There has been an increasing focus in learning interpretable feature representations, particularly in applications such as medical image analysis that require explainability, whilst relying less on annotated data (since annotations can be tedious and costly).

Anatomy Disentanglement

Unsupervised Data Selection for Supervised Learning

no code implementations29 Oct 2018 Gabriele Valvano, Andrea Leo, Daniele Della Latta, Nicola Martini, Gianmarco Santini, Dante Chiappino, Emiliano Ricciardi

Recent research put a big effort in the development of deep learning architectures and optimizers obtaining impressive results in areas ranging from vision to language processing.

Cannot find the paper you are looking for? You can Submit a new open access paper.