Deep learning has produced state-of-the-art results for a variety of tasks. While such
approaches for supervised learning have performed well, they assume that training and …

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel
annotations to learn supervised models like convolutional neural networks. However …

This work considers the problem of unsupervised domain adaptation in person re-
identification (re-ID), which aims to transfer knowledge from the source domain to the target …

Recognizing wild faces is extremely hard as they appear with all kinds of variations.
Traditional methods either train with specifically annotated variation data from target …

In this work, we address the problem of unsupervised domain adaptation for person re-ID
where annotations are available for the source domain but not for target. Previous methods …

Learning methods are challenged when there is not enough labelled data. It gets worse
when the existing learning data have different distributions in different domains. To deal with …

Abstract Domain adaptation deals with training models using large scale labeled data from a
specific source domain and then adapting the knowledge to certain target domains that have …

Learning semantic segmentation models requires a huge amount of pixel-wise labeling.
However, labeled data may only be available abundantly in a domain different from the …

While huge volumes of unlabeled data are generated and made available in many domains,
the demand for automated understanding of visual data is higher than ever before. Most …

Abstract Deep Metric Learning (DML) proposes to learn metric spaces which encode
semantic similarities as embedding space distances. These spaces should be transferable …