In recent years, deep neural networks have emerged as a dominant machine learning tool for a wide variety of application domains. However, training a deep neural network requires a large amount of labeled data, which is an expensive process in terms of time, labor and human expertise. Domain adaptation or transfer learning algorithms address this challenge by leveraging labeled data in a different, but related source domain, to develop a model for the target domain. Further, the explosive growth of digital data has posed a fundamental challenge concerning its storage and retrieval. Due to its storage and retrieval efficiency, recent years have witnessed a wide application of hashing in a variety of computer vision applications. In this paper, we first introduce a new dataset, Office-Home, to evaluate domain adaptation algorithms. The dataset contains images of a variety of everyday objects from multiple domains. We then propose a novel deep learning framework that can exploit labeled source data and unlabeled target data to learn informative hash codes, to accurately classify unseen target data. To the best of our knowledge, this is the first research effort to exploit the feature learning capabilities of deep neural networks to learn representative hash codes to address the domain adaptation problem. Our extensive empirical studies on multiple transfer tasks corroborate the usefulness of the framework in learning efficient hash codes which outperform existing competitive baselines for unsupervised domain adaptation.

Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.

In the recent years, deep learning algorithms have achieved state-of-the-art performance in a variety of computer vision applications. In this paper, we propose a novel active learning framework to select the most informative unlabeled samples to train a deep belief network model. We introduce a loss function specific to the active learning task and train the model to minimize the loss function. To the best of our knowledge, this is the first research effort to integrate an active learning based criterion in the loss function used to train a deep belief network. Our extensive empirical studies on a wide variety of uni-modal and multi-modal vision datasets corroborate the potential of the method for real-world image recognition applications.