Domain Adaptation as Learning with Auxiliary Information
نویسندگان
چکیده
Many non-standard learning models, such as semi-supervised learning or transfer learning can be viewed as learning with auxiliary information. We discuss how to formally analyze the benefits of auxiliary information and suggest a formal framework for this. Further, we consider a particular case of learning with auxiliary information, namely regularized least squares regression with an extra input hypothesis. This was suggested and first analyzed by Kuzborskij and Orabona [2013] in the context of transfer learning. We extend their analysis by providing a finite sample regret bound.
منابع مشابه
Deep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملImage alignment via kernelized feature learning
Machine learning is an application of artificial intelligence that is able to automatically learn and improve from experience without being explicitly programmed. The primary assumption for most of the machine learning algorithms is that the training set (source domain) and the test set (target domain) follow from the same probability distribution. However, in most of the real-world application...
متن کاملInformation Bottleneck Domain Adaptation with Privileged Information for Visual Recognition
We address the unsupervised domain adaptation problem for visual recognition when an auxiliary data view is available during training. This is important because it allows improving the training of visual classifiers on a new target visual domain when paired additional source data is cheaply available. This is the case when we learn from a source of RGB plus depth data, for then test on a new RG...
متن کاملSample-oriented Domain Adaptation for Image Classification
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. The conventional image processing algorithms cannot perform well in scenarios where the training images (source domain) that are used to learn the model have a different distribution with test images (target domain). Also, many real world applicat...
متن کاملLearning to Adapt Across Multimedia Domains
In multimedia, machine learning techniques are often applied to build models to map low-level feature vectors into semantic labels. As data such as images and videos come from a variety of domains (e.g., genres, sources) with different distributions, there is a benefit of adapting models trained from one domain to other domains in terms of improving performance and reducing computational and hu...
متن کامل