scholarly journals General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer

2017 ◽  
Author(s):  
Yong Luo ◽  
Yonggang Wen ◽  
Tongliang Liu ◽  
Dacheng Tao
Keyword(s):  
Transfer Learning ◽  
Metric Learning ◽  
Learning Task ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Target Domain ◽  
Feature Representations ◽  
Transfer Distance ◽  
Learning Tasks ◽  
Feature Spaces

Transfer learning aims to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. Recently, transfer distance metric learning (TDML) has attracted lots of interests, but most of these methods assume that feature representations for the source and target learning tasks are the same. Hence, they are not suitable for the applications, in which the data are from heterogeneous domains (feature spaces, modalities and even semantics). Although some existing heterogeneous transfer learning (HTL) approaches is able to handle such domains, they lack flexibility in real-world applications, and the learned transformations are often restricted to be linear. We therefore develop a general and flexible heterogeneous TDML (HTDML) framework based on the knowledge fragment transfer strategy. In the proposed HTDML, any (linear or nonlinear) distance metric learning algorithms can be employed to learn the source metric beforehand. Then a set of knowledge fragments are extracted from the pre-learned source metric to help target metric learning. In addition, either linear or nonlinear distance metric can be learned for the target domain. Extensive experiments on both scene classification and object recognition demonstrate superiority of the proposed method.

scholarly journals Weakly Supervised Scene Parsing with Point-Based Distance Metric Learning

2019 ◽  
Vol 33 ◽  
pp. 8843-8850 ◽  
Author(s):  
Rui Qian ◽  
Yunchao Wei ◽  
Honghui Shi ◽  
Jiachen Li ◽  
Jiaying Liu ◽  
...  
Keyword(s):  
Deep Neural Networks ◽  
Metric Learning ◽  
Dependent Manner ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Feature Representations ◽  
Training Images ◽  
Scene Parsing ◽  
Weakly Supervised ◽  
Semantic Scene

Semantic scene parsing is suffering from the fact that pixellevel annotations are hard to be collected. To tackle this issue, we propose a Point-based Distance Metric Learning (PDML) in this paper. PDML does not require dense annotated masks and only leverages several labeled points that are much easier to obtain to guide the training process. Concretely, we leverage semantic relationship among the annotated points by encouraging the feature representations of the intra- and intercategory points to keep consistent, i.e. points within the same category should have more similar feature representations compared to those from different categories. We formulate such a characteristic into a simple distance metric loss, which collaborates with the point-wise cross-entropy loss to optimize the deep neural networks. Furthermore, to fully exploit the limited annotations, distance metric learning is conducted across different training images instead of simply adopting an image-dependent manner. We conduct extensive experiments on two challenging scene parsing benchmarks of PASCALContext and ADE 20K to validate the effectiveness of our PDML, and competitive mIoU scores are achieved.

scholarly journals Online Heterogeneous Transfer Metric Learning

2018 ◽  
Author(s):  
Yong Luo ◽  
Tongliang Liu ◽  
Yonggang Wen ◽  
Dacheng Tao
Keyword(s):  
Metric Learning ◽  
Sequential Data ◽  
Manifold Regularization ◽  
Distance Metric ◽  
Target Domain ◽  
Source Domain ◽  
Feature Representations ◽  
Label Information ◽  
Online Setting ◽  
Effectiveness And Efficiency

Distance metric learning (DML) has been demonstrated to be successful and essential in diverse applications. Transfer metric learning (TML) can help DML in the target domain with limited label information by utilizing information from some related source domains. The heterogeneous TML (HTML), where the feature representations vary from the source to the target domain, is general and challenging. However, current HTML approaches are usually conducted in a batch manner and cannot handle sequential data. This motivates the proposed online HTML (OHTML) method. In particular, the distance metric in the source domain is pre-trained using some existing DML algorithms. To enable knowledge transfer, we assume there are large amounts of unlabeled corresponding data that have representations in both the source and target domains. By enforcing the distances (between these unlabeled samples) in the target domain to agree with those in the source domain under the manifold regularization theme, we learn an improved target metric. We formulate the problem in the online setting so that the optimization is efficient and the model can be adapted to new coming data. Experiments in diverse applications demonstrate both effectiveness and efficiency of the proposed method.

scholarly journals Distance metric learning for graph structured data

2021 ◽  
Author(s):  
Tomoki Yoshida ◽  
Ichiro Takeuchi ◽  
Masayuki Karasuyama
Keyword(s):  
Metric Learning ◽  
Structured Data ◽  
Distance Metric Learning ◽  
Distance Metric

scholarly journals Chi-Squared Distance Metric Learning for Histogram Data

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Wei Yang ◽  
Luhui Xu ◽  
Xiaopan Chen ◽  
Fengbin Zheng ◽  
Yang Liu
Keyword(s):  
Nearest Neighbor ◽  
State Of The Art ◽  
Metric Learning ◽  
Nearest Neighbors ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Projected Gradient Method ◽  
Proper Distance ◽  
Chi Squared ◽  
Real World Datasets

Learning a proper distance metric for histogram data plays a crucial role in many computer vision tasks. The chi-squared distance is a nonlinear metric and is widely used to compare histograms. In this paper, we show how to learn a general form of chi-squared distance based on the nearest neighbor model. In our method, the margin of sample is first defined with respect to the nearest hits (nearest neighbors from the same class) and the nearest misses (nearest neighbors from the different classes), and then the simplex-preserving linear transformation is trained by maximizing the margin while minimizing the distance between each sample and its nearest hits. With the iterative projected gradient method for optimization, we naturally introduce thel2,1norm regularization into the proposed method for sparse metric learning. Comparative studies with the state-of-the-art approaches on five real-world datasets verify the effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document