Open Set Domain Adaptation for Image and Action Recognition

Abstract

Since annotating and curating large datasets is very expensive, there is a need to transfer the knowledge from existing annotated datasets to unlabelled data. Data that is relevant for a specific application, however, usually differs from publicly available datasets since it is sampled from a different domain. While domain adaptation methods compensate for such a domain shift, they assume that all categories in the target domain are known and match the categories in the source domain. Since this assumption is violated under real-world conditions, we propose an approach for open set domain adaptation where the target domain contains instances of categories that are not present in the source domain. The proposed approach achieves state-of-the-art results on various datasets for image classification and action recognition. Since the approach can be used for open set and closed set domain adaptation, as well as unsupervised and semi-supervised domain adaptation, it is a versatile tool for many applications.

References in corpus (11)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• The Kinetics Human Action Video Dataset
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• DeepID3: Face Recognition with Very Deep Neural Networks
• VisDA: The Visual Domain Adaptation Challenge
• Better Mixing via Deep Representations
• Efficient Learning of Domain-invariant Image Representations
• A Testbed for Cross-Dataset Analysis