Publications associées à Multiple discovery

Concept Discovery for The Interpretation of Landscape Scenicness

In this paper, we study how to extract visual concepts to understand landscape scenicness. Using visual feature representations from a Convolutional Neural Network (CNN), we learn a number of Concept Activation Vectors (CAV) aligned with semantic concepts ...

2020

The formation of Coasean institutions to provide university knowledge for innovation: a case study and econometric evidence for Switzerland

Dominique Foray

"Coasean" institutions are an alternative institutional form that provides a solution to some market and coordination failures. As such they can weaken considerably the case for public subsidies in a vast range of context. They are "market-based" and an in ...

SPRINGER2021

Deep Feature Factorization for Concept Discovery

Sabine Süsstrunk, Radhakrishna Achanta, Edo Collins

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical c ...

SpringerLink2018

The hope and the hype of organoid research

Matthias Lütolf, Alfonso Martinez Arias

The recent increase in organoid research has been met with great enthusiasm, as well as expectation, from the scientific community and the public alike. There is no doubt that this technology opens up a world of possibilities for scientific discovery in de ...

Company of Biologists2017

Towards new tuberculosis drugs

Stewart Cole

The need for better drugs to treat tuberculosis has never been greater. Despite insufficient funding for discovery research, intensive efforts have been made to find and develop new lead compounds capable of reducing the duration of the present treatment k ...

2007