Unsupervised Transductive Domain Adaptation
نویسندگان
چکیده
Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain shift between the training and the test data distribution. In this regard, unsupervised domain adaptation algorithms have been proposed to directly address the domain shift problem. In this paper, we approach the problem from a transductive perspective. We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment. We also show that our model can easily be extended for deep feature learning in order to learn features which are discriminative in the target domain. Our experiments show that the proposed method significantly outperforms state-of-the-art algorithms in both object recognition and digit classification experiments by a large margin.
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 کاملTransductive Adaptation of Black Box Predictions
Access to data is critical to any machine learning component aimed at training an accurate predictive model. In reality, data is often a subject of technical and legal constraints. Data may contain sensitive topics and data owners are often reluctant to share them. Instead of access to data, they make available decision making procedures to enable predictions on new data. Under the black box cl...
متن کاملA Comparison of Methods for Transductive Transfer Learning
In this paper we examine the problem of domain adaptation for protein name extraction. First we define the general problem of transfer learning and the particular subproblem of domain adaptation. We then describe some current state of the art supervised and transductive approaches involving support vector machines and maximum entropy models. Using these as inspiration, we turn to the unsupervis...
متن کاملTransductive Transfer Machine
We propose a pipeline for transductive transfer learning and demonstrate it in computer vision tasks. In pattern classification, methods for transductive transfer learning (also known as unsupervised domain adaptation) are designed to cope with cases in which one cannot assume that training and test sets are sampled from the same distribution, i.e., they are from different domains. However, som...
متن کاملLearning finite state word representations for unsupervised Twitter adaptation of POS taggers
Brown clusters enable POS taggers to generalize better to words that did not occur in the labeled data, clustering distributionally similar seen and unseen words, thereby making models more robust to sparsity effects and domain shifts. However, Brown clustering is a transductive clustering method, and OOV effects still arise. Words neither in the labeled data nor in the unlabeled data cannot be...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1602.03534 شماره
صفحات -
تاریخ انتشار 2016