Triplet Loss Network for Unsupervised Domain Adaptation
نویسندگان
چکیده
منابع مشابه
Parameter Reference Loss for Unsupervised Domain Adaptation
The success of deep learning in computer vision is mainly attributed to an abundance of data. However, collecting large-scale data is not always possible, especially for the supervised labels. Unsupervised domain adaptation (UDA) aims to utilize labeled data from a source domain to learn a model that generalizes to a target domain of unlabeled data. A large amount of existing work uses Siamese ...
متن کاملDeep Transfer Network: Unsupervised Domain Adaptation
Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the features (marginal distribution), and the distribution of the labels given features (conditional distribution). In this paper, we propose a new domain adaptat...
متن کاملDeep 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 کاملDeep Hashing Network for Unsupervised Domain Adaptation Supplementary Material
1. Loss Function Derivative In this section we outline the derivative of Equation 8 for the backpropagation algorithm; min U J = L(Us) + γM(Us, Ut) + ηH(Us, Ut), (8) where, U := {Us ∪ Ut} and (γ, η) control the importance of domain adaptation (1) and target entropy loss (7) respectively. In the following subsections, we outline the derivative of the individual terms w.r.t. the input U. 1.1. Der...
متن کاملBoosting for Unsupervised Domain Adaptation
To cope with machine learning problems where the learner receives data from different source and target distributions, a new learning framework named domain adaptation (DA) has emerged, opening the door for designing theoretically well-founded algorithms. In this paper, we present SLDAB, a self-labeling DA algorithm, which takes its origin from both the theory of boosting and the theory of DA. ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Algorithms
سال: 2019
ISSN: 1999-4893
DOI: 10.3390/a12050096