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
Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation
[article]
2020
arXiv
pre-print
One crucial aspect of partial domain adaptation (PDA) is how to select the relevant source samples in the shared classes for knowledge transfer. ...
However, since the domain shift between source and target domains, only using the deep features for sample selection is defective. ...
Related Work Partial Domain Adaptation: Deep DA methods have been widely studied in recent years. ...
arXiv:1905.10756v4
fatcat:a5pylbjgpbf5jcxggyxmuvujfu
Class Subset Selection for Partial Domain Adaptation
2019
Computer Vision and Pattern Recognition
Partial domain adaptation (PDA) investigates the scenarios in which the target label space is a subset of the source label space. ...
Empirical results on Office-31 and Office-Home datasets demonstrate the high potential of the proposed approach in addressing different partial domain adaptation tasks. ...
) [20] , Adversarial Discriminative Domain Adaptation (ADDA) [32] , Importance Weighted Adversarial Nets (IWAN) [38] , Selective Adversarial Network (SAN) [3] , and Partial Adversarial Domain Adaptation ...
dblp:conf/cvpr/ZohrizadehKK19
fatcat:nlqgnobv6zc4jbreewotg3ocae
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
[article]
2023
arXiv
pre-print
To alleviate the above issues, we develop a novel 'Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation. ...
domain adaptation. ...
in partial domain adaptation. ...
arXiv:2012.03358v2
fatcat:h3dynkjwyna3dbtijc5lf24k5m
Partial Domain Adaptation Using Selective Representation Learning For Class-Weight Computation
[article]
2021
arXiv
pre-print
To tackle a more practical and challenging scenario, we formulate the problem statement from a partial domain adaptation perspective, where the source label set is a super set of the target label set. ...
Various domain adaptation techniques exist in literature that bridge this distribution discrepancy. However, a majority of these models require the label sets of both the domains to be identical. ...
) [13] , Selective Adversarial Network (SAN) [2] , Partial Adversarial Domain Adaptation(PADA) [3] and class Subset Selection for Partial Domain Adaptation (SSPDA) [4] . ...
arXiv:2101.02275v1
fatcat:vgpswalrkzhy7obxibrbjww774
Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
[article]
2022
arXiv
pre-print
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. ...
To mitigate these issues, we devise a mechanism for strategic selection of highly-confident target samples essential for the estimation of class-importance weights. ...
Partial domain adaptation (𝑝𝑑𝑎) [1] relaxes this constraint by utilizing a large-scale source domain data that subsumes the target label space. ...
arXiv:2207.08145v1
fatcat:dlobyg4rfzfpddbnesur6zekqi
Source Class Selection With Label Propagation For Partial Domain Adaptation
2021
2021 IEEE International Conference on Image Processing (ICIP)
This problem has been formulated as Partial Domain Adaptation (PDA) in the literature and is a challenging task due to the negative transfer issue (i.e. source-domain data belonging to the irrelevant classes ...
harm the domain adaptation). ...
This problem is well known as Partial Domain Adaptation (PDA) and has been studied in recent literature [4, 5, 6, 7, 8, 9] . ...
doi:10.1109/icip42928.2021.9506752
fatcat:3kh2hda7djhqdn7rvd3h3746bu
Selective Transfer With Reinforced Transfer Network for Partial Domain Adaptation
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
One crucial aspect of partial domain adaptation (PDA) is how to select the relevant source samples in the shared classes for knowledge transfer. ...
However, since the domain shift between source and target domains, only using the deep features for sample selection is defective. ...
Related Work Partial Domain Adaptation: Deep DA methods have been widely studied in recent years. ...
doi:10.1109/cvpr42600.2020.01272
dblp:conf/cvpr/ChenCCJFJ20
fatcat:varze667izdtzcplxpru6bs7lu
From Big to Small: Adaptive Learning to Partial-Set Domains
[article]
2022
arXiv
pre-print
Still, the common requirement of identical class space shared across domains hinders applications of domain adaptation to partial-set domains. ...
Then, we propose Selective Adversarial Network (SAN and SAN++) with a bi-level selection strategy and an adversarial adaptation mechanism. ...
partial domain adaptation. ...
arXiv:2203.07375v1
fatcat:rurl4ukmw5d7vmnptu6hngwj5a
Domain Adversarial Reinforcement Learning for Partial Domain Adaptation
[article]
2019
arXiv
pre-print
Partial domain adaptation aims to transfer knowledge from a label-rich source domain to a label-scarce target domain which relaxes the fully shared label space assumption across different domains. ...
Experiments on several benchmark datasets demonstrate that the superior performance of our DARL method over existing state of the arts for partial domain adaptation. ...
Since there is no labels available in the target domain for the partial domain adaptation task, it is nontrivial for us to perform the source instance selection. ...
arXiv:1905.04094v1
fatcat:rnogtdtamvhpdkxvl7z2l4kxze
A Weighted Partial Domain Adaptation for Acoustic Scene Classification and Its Application in Fiber Optic Security System
2020
IEEE Access
Our method establish a connection between source and target domains to do the partial domain adaptation. ...
In this article, a weighted partial domain adaptation method is proposed to solve the Acoustic Scene Classification (ASC) problem. ...
In order to verify the effect of partial domain adaptation algorithm, the data in the source domain selects all classes of data, while the data in the target domain only selects part classes of data. ...
doi:10.1109/access.2020.3044153
fatcat:smrtlxa6gbbbfi5w7i3w6kf2ai
Domain Adaptation for CRF-based Chinese Word Segmentation using Free Annotations
2014
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
In this paper, we study the problem of obtaining partial annotation from freely available data to help Chinese word segmentation on different domains. ...
The performance can drop significantly when the test domain is different from the training domain. ...
Analysis In this section, we study the effect of Wikipedia on domain adaptation when no data selection is performed, in order to analyze the effect of partially annotated data. ...
doi:10.3115/v1/d14-1093
dblp:conf/emnlp/LiuZCLW14
fatcat:fy5jf3po7feshctfduw65o2ira
Combining Active Learning and Partial Annotation for Domain Adaptation of a Japanese Dependency Parser
2015
Proceedings of the 14th International Conference on Parsing Technologies
We evaluate query strategies based on both full and partial annotation in several domains, and find that they reduce the amount of in-domain training data needed for domain adaptation by up to 75% compared ...
We also show that entropy-based query selection strategies can be combined with partial annotation to annotate informative examples in the new domain without annotating full sentences. ...
Partial Annotation Our goal is to reduce the total cost of preparing data for domain adaptation. We do this by combining partial annotation with active learning. ...
doi:10.18653/v1/w15-2202
dblp:conf/iwpt/FlanneryM15
fatcat:mmwms7deirggjfwqt5xcx3cb3y
Partial Transfer Learning with Selective Adversarial Networks
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Previous methods typically match the whole source domain to the target domain, which are prone to negative transfer for the partial transfer problem. ...
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 ...
This paper presents Selective Adversarial Networks (SAN), which largely extends the ability of deep adversarial adaptation [7] to address partial transfer learning from large- scale domains to small-scale ...
doi:10.1109/cvpr.2018.00288
dblp:conf/cvpr/CaoL0J18
fatcat:fmz7hrkrtncf5nbz5jsnazujge
Time-Domain Convolutive Blind Source Separation Employing Selective-Tap Adaptive Algorithms
2007
EURASIP Journal on Audio, Speech, and Music Processing
First, we propose MMax partial update time-domain convolutive BSS (MMax BSS) algorithm. ...
We demonstrate that the partial update scheme applied in the MMax LMS algorithm for single channel can be extended to multichannel time-domain convolutive BSS with little deterioration in performance and ...
The XM algorithm was motivated by MMax partial update scheme [10] as both select a subset of coefficients for updating in every adaptative iteration. ...
doi:10.1155/2007/92528
fatcat:6u5uonsvmjacxnfu5zgr3q5itu
Partial Transfer Learning with Selective Adversarial Networks
[article]
2017
arXiv
pre-print
Previous methods typically match the whole source domain to the target domain, which are prone to negative transfer for the partial transfer problem. ...
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 ...
This paper presents Selective Adversarial Networks (SAN), which largely extends the ability of deep adversarial adaptation [6] to address partial transfer learning from big domains to small domains. ...
arXiv:1707.07901v1
fatcat:igtak7fqsbhjrm77jhrac7uwhu
« Previous
Showing results 1 — 15 out of 731,714 results