Domain Adaptation for Image Analysis: An Unsupervised Approach Using Boltzmann Machines Trained by Perturbation
نویسندگان
چکیده
In this paper, we apply Restricted Boltzmann Machine and Subspace Restricted Boltzmann Machine to domain adaptation. Moreover, we train these models using the Perturb-and-MAP approach to draw approximate sample from the Gibbs distribution. We evaluate our approach on domain adaptation task between two image corpora: MNIST and Handwritten Character Recognition dataset.
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 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 کاملAdaptive Feature Ranking for Unsupervised Transfer Learning
Transfer Learning is concerned with the application of knowledge gained from solving a problem to a different but related problem domain. In this paper, we propose a method and efficient algorithm for ranking and selecting representations from a Restricted Boltzmann Machine trained on a source domain to be transferred onto a target domain. Experiments carried out using the MNIST, ICDAR and TiCC...
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 کاملSpeaker Recognition by means of Restricted Boltzmann Machine Adaptation
Restricted Boltzmann Machines (RBMs) have shown success in speaker recognition. In this paper, RBMs are investigated in a framework comprising a universal model training and model adaptation. Taking advantage of RBM unsupervised learning algorithm, a global model is trained based on all available background data. This general speaker-independent model, referred to as URBM, is further adapted to...
متن کامل