Search Results for author: Bernardino Romera-Paredes

Found 11 papers, 5 papers with code

A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities

3 code implementations30 May 2019 Simon A. A. Kohl, Bernardino Romera-Paredes, Klaus H. Maier-Hein, Danilo Jimenez Rezende, S. M. Ali Eslami, Pushmeet Kohli, Andrew Zisserman, Olaf Ronneberger

Medical imaging only indirectly measures the molecular identity of the tissue within each voxel, which often produces only ambiguous image evidence for target measures of interest, like semantic segmentation.

Instance Segmentation Medical Image Segmentation +1

A Probabilistic U-Net for Segmentation of Ambiguous Images

7 code implementations NeurIPS 2018 Simon A. A. Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R. Ledsam, Klaus H. Maier-Hein, S. M. Ali Eslami, Danilo Jimenez Rezende, Olaf Ronneberger

To this end we propose a generative segmentation model based on a combination of a U-Net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible hypotheses.

Decision Making Semantic Segmentation

Prototypical Priors: From Improving Classification to Zero-Shot Learning

no code implementations3 Dec 2015 Saumya Jetley, Bernardino Romera-Paredes, Sadeep Jayasumana, Philip Torr

Recent works on zero-shot learning make use of side information such as visual attributes or natural language semantics to define the relations between output visual classes and then use these relationships to draw inference on new unseen classes at test time.

General Classification Zero-Shot Learning

Recurrent Instance Segmentation

no code implementations25 Nov 2015 Bernardino Romera-Paredes, Philip H. S. Torr

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image.

Instance Segmentation Occlusion Handling +1

The Benefit of Multitask Representation Learning

no code implementations23 May 2015 Andreas Maurer, Massimiliano Pontil, Bernardino Romera-Paredes

In particular, focusing on the important example of half-space learning, we derive the regime in which multitask representation learning is beneficial over independent task learning, as a function of the sample size, the number of tasks and the intrinsic data dimensionality.

Representation Learning

Sparse coding for multitask and transfer learning

no code implementations4 Sep 2012 Andreas Maurer, Massimiliano Pontil, Bernardino Romera-Paredes

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning.

Dictionary Learning Transfer Learning

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