Filters








3,272 Hits in 2.8 sec

Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data

Tzu Ming Harry Hsu, Wei Yu Chen, Cheng-An Hou, Yao-Hung Hubert Tsai, Yi-Ren Yeh, Yu-Chiang Frank Wang
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
We address a challenging unsupervised domain adaptation problem with imbalanced cross-domain data.  ...  For standard unsupervised domain adaptation, one typically obtains labeled data in the source domain and only observes unlabeled data in the target domain.  ...  As verified above, a robust unsupervised domain adaptation with the ability to handle imbalanced cross-domain data would be preferable.  ... 
doi:10.1109/iccv.2015.469 dblp:conf/iccv/HsuCHTYW15 fatcat:peyg4gxotzc7tpowtakoxgvhmu

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning [article]

Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen
2021 arXiv   pre-print
Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost.  ...  Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data.  ...  Conclusion In this work, we propose CDSSL: a cross-domain semisupervised learning framework to address the unsupervised domain adaptation for object detection.  ... 
arXiv:1911.07158v5 fatcat:avo3zydua5dalo7e6ggnik3wuy

Integrating Expert Knowledge with Domain Adaptation for Unsupervised Fault Diagnosis [article]

Qin Wang, Cees Taal, Olga Fink
2021 arXiv   pre-print
In this paper, we aim to overcome this limitation by integrating expert knowledge with domain adaptation in a synthetic-to-real framework for unsupervised fault diagnosis.  ...  To overcome this domain gap between the synthetic and real data, in the second step of the proposed framework, an imbalance-robust domain adaptation~(DA) approach is proposed to adapt the model from synthetic  ...  This is achieved by integrating expert knowledge in synthetic data with imbalance-robust domain adaptation for unsupervised fault diagnosis.  ... 
arXiv:2107.01849v1 fatcat:hrz4pn73sfbvzpcy4ih5xr6n5m

Semantic Segmentation of highly class imbalanced fully labelled 3D volumetric biomedical images and unsupervised Domain Adaptation of the pre-trained Segmentation Network to segment another fully unlabelled Biomedical 3D Image stack [article]

Shreya Roy, Anirban Chakraborty
2020 arXiv   pre-print
So in this paper, we have proposed a novel approach in the context of unsupervised domain adaptation while classifying each pixel of the target volumetric data into cell boundary and cell body.  ...  the training original images in the source domain.  ...  Also, we have performed unsupervised domain adaptation on our segmentation network where we considered the target domain data to be fully unlabeled.  ... 
arXiv:2004.02748v1 fatcat:xze2iehnlbbqvh5bra4dheb6zm

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [article]

Taotao Jing, Bingrong Xu, Jingjing Li, Zhengming Ding
2020 arXiv   pre-print
Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness.  ...  To this end, we propose a Towards Fair Knowledge Transfer (TFKT) framework to handle the fairness challenge in imbalanced cross-domain learning.  ...  It highly affirms the effectiveness and robustness of our method dealing with domain adaptation problem in which the source domain data is extremely imbalanced and insufficient for training.  ... 
arXiv:2010.12184v2 fatcat:yenza66qsjfbfggavz7hamjxia

RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems [article]

Cheng Wang, Mathias Niepert, Hui Li
2019 arXiv   pre-print
Data sparsity and data imbalance are practical and challenging issues in cross-domain recommender systems.  ...  Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity  ...  Imbalanced Learning Recently, Imbalanced learning [8] , [9] , [10] , [30] has been adapted to cross-domain data [11] , [12] .  ... 
arXiv:1903.10794v2 fatcat:wy7gqklumjefxn4o36wrkcohzq

Table of contents

2020 IEEE Transactions on Neural Networks and Learning Systems  
Wu Unsupervised Domain Adaptation With Adversarial Residual Transform Networks ........................................ .................................................................................  ...  Dorronsoro 2752 Adaptive Chunk-Based Dynamic Weighted Majority for Imbalanced Data Streams With Concept Drift ................ ........................................................................  ... 
doi:10.1109/tnnls.2020.3009705 fatcat:4cm6xswfnrarzezba53tulu62q

Towards Fair Cross-Domain Adaptation via Generative Learning [article]

Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
2020 arXiv   pre-print
To perform fair cross-domain adaptation and boost the performance on these minority categories, we develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification  ...  Specifically, generative feature augmentation is explored to synthesize effective training data for few-shot source classes, while effective cross-domain alignment aims to adapt knowledge from source to  ...  Unsupervised Domain Adaptation Unsupervised DA aims to bridge the distribution difference between domains with unlabeled target domain data.  ... 
arXiv:2003.02366v2 fatcat:73q2wegggjhixo462wya2czore

Mining Label Distribution Drift in Unsupervised Domain Adaptation [article]

Peizhao Li, Zhengming Ding, Hongfu Liu
2020 arXiv   pre-print
Unsupervised domain adaptation targets to transfer task knowledge from labeled source domain to related yet unlabeled target domain, and is catching extensive interests from academic and industrial areas  ...  Next, we propose Label distribution Matching Domain Adversarial Network (LMDAN) to handle data distribution shift and label distribution drift jointly.  ...  The goal of unsupervised domain adaptation is to utilize labeled source data for unlabeled target samples predictions.  ... 
arXiv:2006.09565v1 fatcat:pkpzkxeiijhqfas3h23zjh5rcy

NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications [article]

Guangyi Xiao, Weiwei Xiang, Huan Liu, Hao Chen, Shun Peng, Jingzhi Guo, Zhiguo Gong
2021 arXiv   pre-print
data with non-shared and imbalanced classes to specified small and imbalanced applications (NI-UDA), where non-shared classes mean the label space out of the target domain.  ...  We propose a new general Graph Adversarial Domain Adaptation (GADA) based on semantic knowledge reasoning of class structure for solving the problem of unsupervised domain adaptation (UDA) from the big  ...  big data is adapted to some imbalanced target domains.  ... 
arXiv:2108.05061v2 fatcat:ty73gwywhvhgfcpxvpsty2g2vm

Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift [article]

Qinming Zhang, Luyan Liu, Kai Ma, Cheng Zhuo, Yefeng Zheng
2020 arXiv   pre-print
In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy.  ...  To further reduce the accumulated error, we introduce a class-imbalanced cross learning using most confident predictions at the class-level.  ...  Class-imbalanced Cross Learning In case of unsupervised domain adaptation with ambiguous labels, it is more challenging to esimate the results accurately.  ... 
arXiv:2006.10990v1 fatcat:4pfw3n4wu5he7krp57yp3lrtry

Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift

Qinming Zhang, Luyan Liu, Kai Ma, Cheng Zhuo, Yefeng Zheng
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy.  ...  To further reduce the accumulated error, we introduce a class-imbalanced cross learning using most confident predictions at class-level.  ...  Class-imbalanced Cross Learning In case of unsupervised domain adaptation with ambiguous labels, it is more challenging to esimate the results accurately.  ... 
doi:10.24963/ijcai.2020/146 dblp:conf/ijcai/ZhangLMZZ20 fatcat:vtl34xuwojcy5l6pmlytxpnq6q

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation [article]

Taotao Jing, Zhengming Ding
2020 arXiv   pre-print
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain.  ...  To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment.  ...  Conclusion We presented a novel Adversarial Dual Distinct Classifier Networks (AD 2 CN) for unsupervised domain adaptation to align source and target domain distribution discrepancy as well as task-specific  ... 
arXiv:2008.11878v1 fatcat:rvo2ywslhrcvln2gr2wyhbdqvu

UNSUPERVISED DOMAIN ADAPTATION USING A TEACHER-STUDENT NETWORK FOR CROSS-CITY CLASSIFICATION OF SENTINEL-2 IMAGES

J. Hu, L. Mou, X. X. Zhu
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Unsupervised domain adaptation is a potential solution for this issue.  ...  In this paper, we attempt to adapt the unsupervised domain adaptation strategy by using a teacher-student network, mean teacher model, to investigate a cross-city classification problem in remote sensing  ...  This paper attempts to adapt an end-to-end unsupervised domain adaptation model, the mean teacher model, to solve the cross-city problem.  ... 
doi:10.5194/isprs-archives-xliii-b2-2020-1569-2020 fatcat:36s4delgbrcpbl6h3tfvi6flbm

Deep Domain Adaptive Object Detection: a Survey [article]

Wanyi Li, Fuyu Li, Yongkang Luo, Peng Wang, Jia sun
2020 arXiv   pre-print
This paper aims to review the state-of-the-art progress on deep domain adaptive object detection approaches. Firstly, we introduce briefly the basic concepts of deep domain adaptation.  ...  Deep domain adaptive object detection (DDAOD) has emerged as a new learning paradigm to address the above mentioned challenges.  ...  Thus, it worth conducting more research such as adaptation from visible domain with large amount of labeled data to thermal infrared domain for which annotated data is expensive to collect.  ... 
arXiv:2002.06797v3 fatcat:mozths3lk5djndue6dzefxuq3q
« Previous Showing results 1 — 15 out of 3,272 results