Filters








38,390 Hits in 5.3 sec

Deep Domain Adaptive Object Detection: a Survey [article]

Wanyi Li, Fuyu Li, Yongkang Luo, Peng Wang, Jia sun
2020 arXiv   pre-print
These methods typically assume that large amount of labeled training data is available, and training and test data are drawn from an identical distribution.  ...  Secondly, the deep domain adaptive detectors are classified into five categories and detailed descriptions of representative methods in each category are provided.  ...  Lin et.al [17] introduced a multi-modal structure-consistent image-to-image translation model to realize domain adaptive vehicle detection.  ... 
arXiv:2002.06797v3 fatcat:mozths3lk5djndue6dzefxuq3q

Category-Sensitive Domain Adaptation for Land Cover Mapping in Aerial Scenes

Bo Fang, Rong Kou, Li Pan, Pengfei Chen
2019 Remote Sensing  
Meanwhile, the CtALN aims to learn a semantic labeling model in the target domain with the translated features and corresponding reference labels.  ...  consistency between labeled and unlabeled images in the feature space.  ...  Geometry-Consistency In unsupervised domain adaptation tasks, t property of images that simple geometric trans Here, the semantic structure refers to the inform which can easily be perceived by humans  ... 
doi:10.3390/rs11222631 fatcat:gbkmgj7qe5dhjmg44uiqptghbu

Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer

Arthita Ghosh, Max Ehrlich, Larry Davis, Rama Chellappa
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
To this end, we propose an unsupervised domain adaptation based approach using adversarial learning.  ...  This can potentially aid in semantic as well as material label transfer from a richly annotated source to a target domain.  ...  We use deep domain adaptation techniques for unsupervised super-resolution and semantic label transfer from a small, high resolution, richly annotated source domain to a larger, low resolution target domain  ... 
doi:10.1109/igarss.2019.8900639 dblp:conf/igarss/GhoshE0C19 fatcat:awikkzhaj5cgjc2lnydok43uoe

BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments [article]

Divya Kothandaraman, Rohan Chandra, Dinesh Manocha
2021 arXiv   pre-print
Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.  ...  We describe a new semantic segmentation technique based on unsupervised domain adaptation (DA), that can identify the class or category of each region in RGB images or videos.  ...  Architecture: Consistent with adversarial domain adaptation [42] , our network consists of a DNN for semantic segmentation, and domain discriminators.  ... 
arXiv:2010.03523v3 fatcat:72sr7avhhjb7niwkheizlc2eeu

Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation [article]

Cheng Chen, Qi Dou, Hao Chen, Pheng-Ann Heng
2018 arXiv   pre-print
Our domain adaptation procedure is unsupervised, without using any target domain labels.  ...  The adversarial learning of our network is guided by a GAN loss for mapping data distributions, a cycle-consistency loss for retaining pixel-level content, and a semantic-aware loss for enhancing structural  ...  Fig. 1 . 1 The overview of our unsupervised domain adaptation framework.  ... 
arXiv:1806.00600v2 fatcat:fg6qdglnh5d4bgshjdkt34rzc4

Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-Ray Segmentation [chapter]

Cheng Chen, Qi Dou, Hao Chen, Pheng-Ann Heng
2018 Lecture Notes in Computer Science  
Our domain adaptation procedure is unsupervised, without using any target domain labels.  ...  The adversarial learning of our network is guided by a GAN loss for mapping data distributions, a cycle-consistency loss for retaining pixel-level content, and a semantic-aware loss for enhancing structural  ...  Fig. 1 . 1 The overview of our unsupervised domain adaptation framework.  ... 
doi:10.1007/978-3-030-00919-9_17 fatcat:cwhhwzhh45bu3e7rsjipptkumy

Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss [article]

Qi Dou, Cheng Ouyang, Cheng Chen, Hao Chen, Pheng-Ann Heng
2018 arXiv   pre-print
In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations.  ...  Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.  ...  Acknowledgments The work described in this paper was supported by the following grants from Hong Kong Research Grants Council under General Research Fund Scheme (Project no. 14202514 and 14203115).  ... 
arXiv:1804.10916v2 fatcat:lzdnmkhtsrgezlxrbricuxu6nq

Unsupervised Domain Adaptation for Dialogue Sequence Labeling Based on Hierarchical Adversarial Training

Shota Orihashi, Mana Ihori, Tomohiro Tanaka, Ryo Masumura
2020 Interspeech 2020  
This paper presents a novel unsupervised domain adaptation method for dialogue sequence labeling.  ...  In order to solve this difficulty, we propose an unsupervised domain adaptation method for dialogue sequence labeling.  ...  To overcome the difficulty in collecting labeled target domain data, we focus on unsupervised domain adaptation that uses both source domain datasets with annotated labels and target domain datasets without  ... 
doi:10.21437/interspeech.2020-2010 dblp:conf/interspeech/OrihashiITM20 fatcat:xlkbbfo7jnf77eripy42h65hgu

Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss

Qi Dou, Cheng Ouyang, Cheng Chen, Hao Chen, Pheng-Ann Heng
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we propose an unsupervised domain adaptation framework with adversarial learning for cross-modality biomedical image segmentations.  ...  Our proposed method is validated by adapting a ConvNet trained with MRI images to unpaired CT data for cardiac structures segmentations, and achieved very promising results.  ...  Acknowledgments The work described in this paper was supported by the following grants from Hong Kong Research Grants Council under General Research Fund Scheme (Project no. 14202514 and 14203115).  ... 
doi:10.24963/ijcai.2018/96 dblp:conf/ijcai/DouOCCH18 fatcat:tkhu6wx3ojf7vcss43ixivbgkq

Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning [article]

Jin Hong, Simon Chun-Ho Yu, Weitian Chen
2021 arXiv   pre-print
Thus, it is desirable to achieve unsupervised domain adaptation for transferring the learned knowledge from the source domain containing labeled CT images to the target domain containing unlabeled MR images  ...  In proposed framework, a network is trained with the above two adversarial losses in an unsupervised manner, and then a mean completer of pseudo-label generation is employed to produce pseudo-labels to  ...  Liping Zhang and Mr. Yongcheng Yao for their valuable comments of this work.  ... 
arXiv:2109.05664v2 fatcat:djavhepndjasngyljuxidy23dm

GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation

Xinhong Ma, Tianzhu Zhang, Changsheng Xu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label.  ...  Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class label  ...  To deal with the above limitations, we propose an endto-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class  ... 
doi:10.1109/cvpr.2019.00846 dblp:conf/cvpr/MaZX19 fatcat:jqlykvdghbelvllzbcaqdbzvoa

Self-Ensemling for 3D Point Cloud Domain Adaption [article]

Qing Li, Xiaojiang Peng, Qi Hao
2021 arXiv   pre-print
the learned knowledge from the labeled source domain to the unlabeled target domain.  ...  Due to the fact that it is difficult to manually annotate a qualitative large-scale 3D point cloud dataset, unsupervised domain adaptation (UDA) is popular in 3D point cloud learning which aims to transfer  ...  Due to the training samples on target domain D t without labels, we employ a simple unsupervised method, named as selfsupervised learning, which is used the consistent structure points as structural representation  ... 
arXiv:2112.05301v1 fatcat:ojeuyp26azd4xmcfqt2kairgfm

Unsupervised domain adaptation for the automated segmentation of neuroanatomy in MRI: a deep learning approach [article]

Philip Novosad, Vladimir Fonov, D. Louis Collins
2019 bioRxiv   pre-print
trained using extensive data augmentation with label-preserving transformations which mimic differences between domains.  ...  This work introduces a new method for unsupervised domain adaptation which improves performance in challenging cross-domain applications without requiring any additional annotations on the target domain  ...  Considering the performance of the baseline network (mean Dice coefficient of 73.2% across all structures and all source → target adaptations), our fully unsupervised method for domain adaptation improved  ... 
doi:10.1101/845537 fatcat:nn4dpm43qrcgjmklarrqfrqpvy

Source Free Unsupervised Graph Domain Adaptation [article]

Haitao Mao, Lun Du, Yujia Zheng, Qiang Fu, Zelin Li, Xu Chen, Shi Han, Dongmei Zhang
2021 arXiv   pre-print
Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification.  ...  Therefore, we propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA).  ...  In computer vision, Source Free Unsupervised Domain Adaptation is a new research task with practical value.  ... 
arXiv:2112.00955v2 fatcat:6frqdhlfpravhkzouhj73q7ftu

Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification [article]

Hsin-Ping Huang, Junyi Jessy Li
2020 arXiv   pre-print
We present an unsupervised adversarial domain adaptive network equipped with a reconstruction component.  ...  Our system outperforms prior works and other adversarial benchmarks for unsupervised domain adaptation. Additionally, we extend our system to take advantage of labeled data if some are available.  ...  Acknowledgments We thank Ray Mooney, Eric Holgate, and the anonymous reviewers for their helpful feedback. This work was partially supported by the NSF Grant IIS-1850153.  ... 
arXiv:2003.02244v2 fatcat:yhfybvujsvf7bekt4ogqowfspu
« Previous Showing results 1 — 15 out of 38,390 results