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.
Filters
OVANet: One-vs-All Network for Universal Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
To learn the inter-and intra-class distance, we propose to train a one-vs-all classifier for each class using labeled source data. ...
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unknown classes which are ...
The idea of employing one-vs-all classifiers is effective for different networks. OVANet needs both open-set and closed-set classifiers. ...
arXiv:2104.03344v4
fatcat:n7yaj2rbxbcntjri7xfspqbuvm
Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox
[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.
Universal domain adaptation (UniDA) is a general unsupervised domain adaptation setting, which addresses both domain and label shifts in adaptation. ...
That is, a multi-class (MC) predictor classifies samples to one of the multiple source classes, while a binary one-vs-all (OVA) predictor further verifies the prediction by MC predictor. ...
Universal Domain Adaptation As for UniDA, we perform UACP on Office-31, Office-Home, VisDA and DomainNet datasets. ...
arXiv:2207.04494v1
fatcat:encctzywqzeihctvbo6qx7vlri
Exploiting Inter-Sample Affinity for Knowability-Aware Universal 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.
Universal domain adaptation (UDA) aims to transfer the knowledge of common classes from source domain to target domain without any prior knowledge on the label set, which requires to distinguish the unknown ...
samples from the known ones in the target domain. ...
The latest work OVANet [22] , proposed by Saito et al., trained a one-vs-all classifier for each class using labeled source samples and adapted the open-set classifier to the target domain. ...
arXiv:2207.09280v1
fatcat:j73lct23rzfzbgihqo7snaxfoe
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning ...
, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research. ...
In European Conference on
[158] Kuniaki Saito and Kate Saenko. OVANet: One-vs-All Net- Computer Vision (ECCV), 2020. 12
work for Universal Domain Adaptation. ...
arXiv:2112.03241v1
fatcat:uzlehddvuvfwzf4dfbjimja45e