A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Domain Adaptation Based on Source-guided Discrepancy
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. ...
To mitigate these problems, we propose a novel discrepancy called source-guided discrepancy (S-disc), which exploits labels in the source domain. ...
Conclusion We proposed a novel discrepancy measure for unsupervised domain adaptation called source-guided discrepancy (S-disc). ...
arXiv:1809.03839v3
fatcat:ldh2v7hcbrhnfhnrool2n3igne
Unsupervised Domain Adaptation Based on Source-Guided Discrepancy
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To mitigate these problems, this paper proposes a novel discrepancy measure called source-guided discrepancy (S-disc), which exploits labels in the source domain unlike the existing ones. ...
An important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. ...
Conclusion We proposed a novel discrepancy measure for unsupervised domain adaptation called source-guided discrepancy (S-disc). ...
doi:10.1609/aaai.v33i01.33014122
fatcat:nto6potizzbi3f5bvousomoy3i
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. ...
To measure the domain discrepancy for asymmetric label space between S and T, we propose Semantic-Guided Matching Discrepancy (SGMD), which first employs instance matching between S and T, and then the ...
Related Work Deep unsupervised domain adaptation. ...
arXiv:1904.08631v1
fatcat:uqurk2ceevg4dhvg2kdvcibrly
Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T . ...
To measure the domain discrepancy for asymmetric label space between S and T , we propose Semantic-Guided Matching Discrepancy (SGMD), which first employs instance matching between S and T , and then the ...
Related Work Deep unsupervised domain adaptation. ...
doi:10.1109/cvpr.2019.00084
dblp:conf/cvpr/ZhuoWCH19
fatcat:6xfpdkhp3rgfnpclnjkcsqx24e
Transferrable Prototypical Networks for Unsupervised Domain Adaptation
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a remold of the distances ...
Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions ...
In particular, one common deep solution for unsupervised domain adaptation is to guide the feature learning in DCNNs by minimizing the domain discrepancy with Maximum Mean Discrepancy (M-MD) [6] . ...
doi:10.1109/cvpr.2019.00234
dblp:conf/cvpr/PanYLWNM19
fatcat:uijemqaydjcf5e4t2tnbybnhje
Transferrable Prototypical Networks for Unsupervised Domain Adaptation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a remold of the distances ...
Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions ...
In particular, one common deep solution for unsupervised domain adaptation is to guide the feature learning in DCNNs by minimizing the domain discrepancy with Maximum Mean Discrepancy (MMD) [6] . ...
arXiv:1904.11227v1
fatcat:eveiyypusbenhjkogdie53ubem
Improving Domain-Specific Classification by Collaborative Learning with Adaptation Networks
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
For unsupervised domain adaptation, the process of learning domain-invariant representations could be dominated by the labeled source data, such that the specific characteristics of the target domain may ...
domain discrepancy. ...
Recently, CNN-based methods have become a mainstream technique for unsupervised visual domain adaptation. Many works focus on reducing the discrepancy between domains. ...
doi:10.1609/aaai.v33i01.33015450
fatcat:cty6d7r3ivbtbcmtzclvcy6lrq
Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We evaluate the proposed method on several unsupervised domain adaption benchmarks and achieve superior or comparable performance to state-of-the-art results. ...
Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set. ...
Related Work For unsupervised domain adaption, the main approach is to guide the feature learning by minimizing the difference between the distributions of source domain and target domain. ...
arXiv:1811.12751v1
fatcat:quexyypeovbvndgu4wzrlutt2u
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation ...
We validate the effectiveness of our method on several adaptation tasks including object recognition and semantic segmentation. ...
In this paper, we aim to solve unsupervised domain adaptation challenges when domain discrepancy is large due to variation across the source and the target domains. c 2020. ...
arXiv:1906.02238v2
fatcat:rlzxckwruzcjhad66p2mwmvxse
Deep Unsupervised Convolutional Domain Adaptation
2017
Proceedings of the 2017 ACM on Multimedia Conference - MM '17
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Signi cant research endeavors have been devoted to aligning the feature distributions between the source and the target domains in the top fully connected layers based on unsupervised DNN-based models. ...
The domain discrepancy, measured in correlation alignment loss, is minimized on the second-order correlation statistics of the attention maps for both source and target domains. ...
knowledge, signi cant research endeavors have been devoted to aligning the feature distributions between the source and the target domains on the top FC layers based on unsupervised DNN-based domain adaptation ...
doi:10.1145/3123266.3123292
dblp:conf/mm/ZhuoWZH17
fatcat:f6j4lbgchfb2fdv5y52yfsxtwa
Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Unsupervised domain adaptation has been proposed to alleviate this problem by aligning the distribution between labeled source domain and unlabeled target domain. ...
In this paper, we propose triplet loss guided adversarial domain adaptation method (TLADA) for bearing fault diagnosis by jointly aligning the data-level and class-level distribution. ...
Unsupervised Domain Adaptation Unsupervised domain adaptation aims to alleviate the domain shift problem by aligning the distribution between the labeled source domain and the unlabeled target domain. ...
doi:10.3390/s20010320
pmid:31935949
pmcid:PMC6983071
fatcat:pjh72eexqfgvnoppk7v5okoze4
Adversarial-Prediction Guided Multi-task Adaptation for Semantic Segmentation of Electron Microscopy Images
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Since no label is available on target domain, we learn an encoding representation not only for the supervised segmentation on source domain but also for unsupervised reconstruction of the target data. ...
In this study, we introduce an adversarial-prediction guided multi-task network to learn the adaptation of a well-trained model for use on a novel unlabeled target domain. ...
To reduce domain discrepancy, there have been a lot of studies focusing on unsupervised domain adaptation (UDA) *Corresponding author. ...
arXiv:2004.02134v1
fatcat:tfr5yqqpebglngqzsn2u56ngf4
Deep visual unsupervised domain adaptation for classification tasks: a survey
2020
IET Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into ...
To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. ...
Other work on this topic [21] presents an unsupervised deep domain adaptation method based on CORAL and MMD. ...
doi:10.1049/iet-ipr.2020.0087
fatcat:x7v5et3r6nagpe2ivuu5nd4qku
Bi-Directional Generation for Unsupervised Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. ...
domains to bridge source and target domains. ...
To
Comparison Results The classification accuracy on the Office-31 dataset for unsupervised domain adaptation based on ResNet-50 are shown in Table 1 . ...
arXiv:2002.04869v1
fatcat:ltbdjklmkjhahj5yosteoxfxw4
Bi-Directional Generation for Unsupervised Domain Adaptation
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. ...
domains to bridge source and target domains. ...
To
Comparison Results The classification accuracy on the Office-31 dataset for unsupervised domain adaptation based on ResNet-50 are shown in Table 1 . ...
doi:10.1609/aaai.v34i04.6137
fatcat:txcnnf2oyngxvh5n4ypzqegefu
« Previous
Showing results 1 — 15 out of 5,268 results