A Novel Transfer Learning Method Based on Common Space Mapping and Weighted Domain Matching

Liang, Ru‐Ze; Xie, Wei; Li, Weizhi; Wang, Hongqi; Wang, Jim Jing-Yan; Taylor, L.

doi:10.1109/ictai.2016.0053

Cited by 25 publications

(9 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments of the problems of image annotation and image retrieval based on image tag completion over three benchmark data sets show the advantage of the proposed method. In the future, we will extend our work of CNN model to other machine learning problems beside image tag completion, such as computer vision [16,5,30,40,22,38,39], material engineering [32,33], portfolio choices [26,25,27,24,28], and biomedical engineering [4,3,2,1,21,13,10,23,12,31,29,9].…”

Section: Discussionmentioning

confidence: 99%

A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

Geng¹,

Zhang

et al. 2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

Geng¹,

Zhang

et al. 2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each triplet contains a basic histogram, a positive histogram, and a negative histogram. But in the final objective, the basic histogram has vanished in (24). The loss function is only the function of the bins of the positive and negative.…”

Section: Proposed Methodsmentioning

confidence: 99%

Stochastic learning of multi-instance dictionary for earth mover’s distance-based histogram comparison

Fan

Liang

2016

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Dictionary plays an important role in multi-instance data representation. It maps bags of instances to histograms. Earth mover's distance (EMD) is the most effective histogram distance metric for the application of multiinstance retrieval. However, up to now, there is no existing multi-instance dictionary learning methods designed for EMD based histogram comparison. To fill this gap, we develop the first EMD-optimal dictionary learning method using stochastic optimization method. In the stochastic learning framework, we have one triplet of bags, including one basic bag, one positive bag, and one negative bag. These bags are mapped to histograms using a multi-instance dictionary. We argue that the EMD between the basic histogram and the positive histogram should be smaller than that between the basic histogram and the negative histogram. Base on this condition, we design a hinge loss. By minimizing this hinge loss and some regularization terms of the dictionary, we update the dictionary instances. The experiments over multi-instance retrieval applications shows its effectiveness when compared to other dictionary learning methods over the problems of medical image retrieval and natural language relation classification.

show abstract

“…Then k i and k m are assigned with continuous id, loaded to the ordered task set {OT } and removed from K. This process is repeated until all tasks are sorted. When |K| = 0, the set {OT } contains all the ordered tasks (line [3][4][5][6][7][8][9][10][11][12]. For each service provider, v i , in sorted candidate set, we feed it with tasks until the budget limit is reached.…”

Section: B Task Allocation Algorithm Designmentioning

confidence: 99%

“…II. RELATED WORK With prevalence of computing infrastructures, mobile systems, such as smartphones, benefit from various emerging technologies [1]- [4]. However, the limited onboard resources, such as battery life, network bandwidth, and storage capacity obstruct mobile devices from various applications.…”

Section: Introductionmentioning

confidence: 99%

EDOS: Edge Assisted Offloading System for Mobile Devices

Harvey

Mao

Hou

et al. 2017

2017 26th International Conference on Computer Communication and Networks (ICCCN)

View full text Add to dashboard Cite

Abstract-Offloading resource-intensive jobs to the cloud and nearby users is a promising approach to enhance mobile devices. This paper investigates a hybrid offloading system that takes both infrastructure-based networks and Ad-hoc networks into the scope. Specifically, we propose EDOS, an edge assisted offloading system that consists of two major components, an Edge Assistant (EA) and Offload Agent (OA). EA runs on the routers/towers to manage registered remote cloud servers and local service providers and OA operates on the users' devices to discover the services in proximity. We present the system with a suite of protocols to collect the potential service providers and algorithms to allocate tasks according to user-specified constraints. To evaluate EDOS, we prototype it on commercial mobile devices and evaluate it with both experiments on a small-scale testbed and simulations. The results show that EDOS is effective and efficient for offloading jobs.

show abstract

A Novel Transfer Learning Method Based on Common Space Mapping and Weighted Domain Matching

Cited by 25 publications

References 51 publications

A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

Stochastic learning of multi-instance dictionary for earth mover’s distance-based histogram comparison

EDOS: Edge Assisted Offloading System for Mobile Devices

Contact Info

Product

Resources

About