Recognizing visual unseen classes, ie for which no training data is available, is known as
Zero Shot Learning (ZSL). Some of the best performing methods apply the triplet loss to …

Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this
paper, we propose two ZSL frameworks that learn to synthesize parameters for novel …

Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual
training data for a part of the classes from a dataset. When the number of classes is large …

Cette thèse porte sur la reconnaissance visuelle" zero-shot", qui vise à classifier des images
de catégories non rencontrées par le modèle pendant la phase d'apprentissage. Après avoir …

Hashtags, usually, are one among the everyday patterns in web-based locale lives. They're
often used with pictures or writings through web-based networking social media. They are …

Measuring similarity between any two entities is an essential component in most machine
learning tasks. This thesis describes a set of techniques revolving around the notion of …

Dans cette thèse nous étudions différentes questions relatives à la mise en pratique de
modèles d'apprentissage profond. En effet malgré les avancées prometteuses de ces …