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
Partial Transfer Learning with Selective Adversarial Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
We present Selective Adversarial Network (SAN), which simultaneously circumvents negative transfer by selecting out the outlier source classes and promotes positive transfer by maximally matching the data ...
Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. ...
Conclusion This paper presented a novel selective adversarial network approach to partial transfer learning. ...
arXiv:1707.07901v1
fatcat:igtak7fqsbhjrm77jhrac7uwhu
Partial Transfer Learning with Selective Adversarial Networks
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
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 present Selective Adversarial Network (SAN), which simultaneously circumvents negative transfer by selecting out the outlier source classes and promotes positive transfer by maximally matching the data ...
Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. ...
Conclusion This paper presented a novel selective adversarial network approach to partial transfer learning. ...
doi:10.1109/cvpr.2018.00288
dblp:conf/cvpr/CaoL0J18
fatcat:fmz7hrkrtncf5nbz5jsnazujge
Domain Adversarial Reinforcement Learning for Partial 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.
To address this issue, we propose a Domain Adversarial Reinforcement Learning (DARL) framework to automatically select source instances in the shared classes for circumventing negative transfer as well ...
Moreover, domain adversarial learning is introduced to learn domain-invariant features for the selected source instances by the agent and the target instances, and also to determine rewards for the agent ...
The Domain Adversarial Reinforcement Learning (DARL) framework is proposed to select source instances with the class labels y s i ∈ Y t and learn transferable features of the selected source instances ...
arXiv:1905.04094v1
fatcat:rnogtdtamvhpdkxvl7z2l4kxze
Class Subset Selection for Partial Domain Adaptation
2019
Computer Vision and Pattern Recognition
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.
Inspired by the idea of subset selection, we propose an adversarial PDA approach which aims to not only automatically select the most relevant subset of source domain classes but also ignore the samples ...
The main purpose of the PDA is to identify the shared classes between the domains and promote learning transferable knowledge from these classes. ...
Figure 1 : 1 Figure 1: Overview of the proposed adversarial network for partial transfer learning. ...
dblp:conf/cvpr/ZohrizadehKK19
fatcat:nlqgnobv6zc4jbreewotg3ocae
Multi-adversarial Partial Transfer Learning with Object-level Attention Mechanism for Unsupervised Remote Sensing Scene Classification
2020
IEEE Access
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 context, Multi-adversarial Object-level Attention Network (MOAN) is proposed for partial transfer learning and selecting useful features. ...
INDEX TERMS Partial transfer learning, domain adaption, object-level attention, remote sensing scene classification, multi-adversarial learning, convolutional neural networks. 56650 This work is licensed ...
UNSUPERVISED PARTIAL TRANSFER LEARNING WITH MULTI-ADVERSARIAL NETWORKS Partial transfer learning is proposed for the situation that the label space in source domain, L s , is bigger than that in target ...
doi:10.1109/access.2020.2982034
fatcat:3exnuyctpvdzjgpj6alwmk7soi
Partial Adversarial Domain Adaptation
[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.
Existing domain adversarial networks generally assume identical label space across different domains. ...
Domain adversarial learning aligns the feature distributions across the source and target domains in a two-player minimax game. ...
We compare the performance of PADA with state-of-the-art transfer learning and deep learning methods: ResNet-50 [29] , Deep Adaptation Network (DAN) [7] , Residual Transfer Networks (RTN) [8] , Domain ...
arXiv:1808.04205v1
fatcat:yxjehnhjjzhx5p26b62vibdc2q
A Survey on Deep Transfer Learning
[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 2020; you can also visit the original URL.
The file type is application/pdf.
This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. ...
Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem ...
transfer learning Instances-based deep transfer learning refers to use a specific weight adjustment strategy, select partial instances from the source domain as supplements to the training set in the ...
arXiv:1808.01974v1
fatcat:pdkq4uskazhslopclb5zhmeigi
Learning to Transfer Examples for Partial 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 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
With domain adversarial training, deep networks can learn disentangled and transferable features that effectively diminish the dataset shift between the source and target domains for knowledge transfer ...
In this work, we propose a unified approach to PDA, Example Transfer Network (ETN), which jointly learns domain-invariant representations across the source and target domains, and a progressive weighting ...
Selective Adversarial Network (SAN) [5] adopts multiple adversarial networks with a weighting mechanism to select out source examples in the outlier classes. ...
arXiv:1903.12230v2
fatcat:v3uigwywanc2flzkhakmt5ett4
From Big to Small: Adaptive Learning to Partial-Set Domains
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Then, we propose Selective Adversarial Network (SAN and SAN++) with a bi-level selection strategy and an adversarial adaptation mechanism. ...
The bi-level selection strategy up-weighs each class and each instance simultaneously for source supervised training, target self-training, and source-target adversarial adaptation through the transferable ...
SELECTIVE ADVERSARIAL NETWORK Motivated by the theoretical analysis, we present Selective Adversarial Network (SAN) and its improved version (SAN++) with the bi-level selection mechanism. ...
arXiv:2203.07375v1
fatcat:rurl4ukmw5d7vmnptu6hngwj5a
Class Conditional Alignment for Partial 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.
Comprehensive experiments on three benchmark datasets Office-31, Office-Home, and Caltech-Office corroborate the effectiveness of the proposed approach in addressing different partial transfer learning ...
The main purpose of PDA is to identify the shared classes between the domains and promote learning transferable knowledge from these classes. ...
[37] , Multi-Adversarial Domain Adaptation (MADA) [23] , Selective Adversarial Network (SAN) [27] , Partial Adversarial Domain Adaptation (PADA) [25] , and Example Transfer Network (ETN) [38] . ...
arXiv:2003.06722v1
fatcat:ekvl2xnnfzagjhjmqc6aclqxvi
Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Furthermore, we capture class-discriminative and domain-invariant features by coupling the process of achieving compact and distinct class distributions with an adversarial objective. ...
In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. ...
Adversarial Network (SAN) [1] , Partial Adversarial Domain Adaptation(PADA) [2] and Example Transfer Network (ETN) [3] . ...
arXiv:2207.08145v1
fatcat:dlobyg4rfzfpddbnesur6zekqi
Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
In this work, we try to address these issues by coupling variational information and adversarial learning with a pseudo-labeling technique to enforce class distribution alignment and minimize the transfer ...
Samples with categories private to the source domain thwart relevant knowledge transfer and degrade model performance. ...
Weighted Adversarial Nets (IWAN) [14] , Selective Adversarial Network (SAN) [3] , Partial Adversarial Domain Adaptation(PADA) [4] and class Subset Selection for Partial Domain Adaptation (SSPDA) ...
arXiv:2212.01590v1
fatcat:tmdv6uy3sjhezetof4a2euabki
On the Role of Contrastive Representation Learning in Adversarial Robustness: An Empirical Study
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
This advantage comes with the price of false negative-pair selection without any label information. ...
However, aside from accuracy, there is a lack of understanding about the impacts of adversarial training on the representations learned by these learning schemes. ...
We use ResNet-50 as the base encoder for all scenarios and a two-layers MLP network as the projection head. Our loss is optimized using the Adam optimizer with a learning rate of 0.0003. ...
arXiv:2302.02502v1
fatcat:xme2cm46jfh6nkmupzgruhxmxq
AIDA: Legal Judgment Predictions for Non-Professional Fact Descriptions via Partial-and-Imbalanced Domain Adaptation
[article]
2023
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 2023; you can also visit the original URL.
The file type is application/pdf.
However, due to the negative transfer of samples in non-shared classes, it is hard for current domain adaptation model to solve the partial-and-imbalanced transfer problem. ...
We propose to embed a novel pArtial Imbalanced Domain Adaptation technique (AIDA) in the deep learning model, which can jointly borrow sibling knowledge from non-shared classes to shared classes in the ...
Selective Adversarial Network (SAN) [8] adopts multiple adversarial networks with weighting mechanism to select out source examples in the non-share classes. ...
arXiv:2302.07728v1
fatcat:lxpc5mwmf5dkljha7w5uepq4de
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.
Partial adversarial-based methods partial adversarial networks SAN [89], PADA [90], IWAN [91], ETN [92] Bold highlights three particular approaches. ...
To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. ...
[89] proposed selective adversarial network (SAN), which improves positive transfer by considering a weighting mechanism via multiple adversarial networks, and tries to prevent the negative transfer ...
doi:10.1049/iet-ipr.2020.0087
fatcat:x7v5et3r6nagpe2ivuu5nd4qku
« Previous
Showing results 1 — 15 out of 31,255 results