Zero-shot remote sensing scene classification aims to solve the scene classification problem
on unseen categories and has attracted numerous research attention in the remote sensing …

Object detection is crucial in aerial imagery analysis. Previous methods based on
convolutional neural networks (CNNs) require large-scale labeled datasets for training to …

Sentence embeddings are an important component of many natural language processing
(NLP) systems. Like word embeddings, sentence embeddings are typically learned on large …

Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and
unseen classes, when only the labeled examples from seen classes are provided. Recent …

A family of loss functions built on pair-based computation have been proposed in the
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …

We present a conceptually simple, flexible, and general framework for few-shot learning,
where a classifier must learn to recognise new classes given only few examples from each …

Suffering from the extreme training data imbalance between seen and unseen classes, most
of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging …

Due to the importance of zero-shot learning, ie, classifying images where there is a lack of
labeled training data, the number of proposed approaches has recently increased steadily …

Deep embeddings answer one simple question: How similar are two images? Learning
these embeddings is the bedrock of verification, zero-shot learning, and visual search. The …

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature
space to a semantic embedding space (eg attribute space). However, such a projection …