OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

Truong, Thanh-Dat; Chappa, Ravi Teja Nvs; Nguyen, Xuan-Bac; Le, Ngan; Dowling, Ashley P. G.; Luu, Khoa

doi:10.1109/icpr56361.2022.9956335

Cited by 5 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our computer vision system functions as an automated detection model capable of classifying defects and contaminated carcasses. While detection, segmentation, and classification are widespread tasks in computer vision Dong et al (2021) ; Zhou et al (2021) ; Le et al (2022) , they have focused on various tasks such as autonomous driving Le et al (2017b , c ); Janai et al (2020) ; Tong et al (2020) ; Truong et al (2022) ; Nguyen et al (2022) , surveillance Gabeur et al (2020) ; Wray et al (2021) ; Yamazaki et al (2022) ; Vo et al (2022) , biometrics Le and Savvides (2016) ; Le et al (2017a) ; Duong et al (2019a , b ); Quach et al (2022) , and medical imaging Han et al (2017) ; Le et al (2018) ; Tran et al (2022b) ; Le et al (2023) ; Thang Pham et al (2023) ; Nguyen et al (2023) , amodal understanding Tran et al (2022a) which mainly target humans, car, objects, face, human organs. None of them target analyzing poultry carcass condemnations defects .…”

Section: Introductionmentioning

confidence: 99%

CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect

Tran,

Truong,

Fernandes

et al. 2024

Poultry Science

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect

Tran,

Truong,

Fernandes

et al. 2024

Poultry Science

View full text Add to dashboard Cite

Subdomain adaptation via correlation alignment with entropy minimization for unsupervised domain adaptation

Gilo,

Mathew,

Mondal

et al. 2024

Pattern Anal Applic

View full text Add to dashboard Cite

RDAOT: Robust Unsupervised Deep Sub-Domain Adaptation Through Optimal Transport for Image Classification

Gilo,

Mathew,

Mondal

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In traditional machine learning, the training and testing data are assumed to come from the same independent and identical distributions. This assumption, however, does not hold up in realworld applications, as differences between the training and testing data may have different distributions. Domain adaptation has emerged as a solution that enables the transfer of knowledge between domains with distinct distributions. In this paper, we primarily utilize domain adaptation in the context of visual recognition tasks despite its growing application in diverse domains. Earlier studies have mainly aimed at minimizing the differences in global distributions between the domains and failed to capture the local, pertinent features crucial for domain alignment. Furthermore, models struggle to perform well and generalize to target data when outliers or noise exist in the datasets. This work addresses these problems and provides unique strategies for unsupervised domain adaptation using RDAOT (Robust Deep Adaptation via Optimal Transport). To capture local information by utilizing LMMD (Local Maximum Mean Discrepancy) to minimize the divergence of the feature distributions between the domains. We examine label noise robustness in the source domain and ROT (Robust Optimal Transport) loss to preserve robustness in domain adaptation, which lessens the cost of transporting source distributions to the target distributions. The significance of our presented technique was assessed through extensive experiments on six different visual recognition domain adaptation datasets. The results demonstrate that our method outperforms the current state-of-the-art techniques, indicating superior performance. Our approach was evaluated against several baselines, and the results significantly improved average accuracy across various datasets. Specifically, the average accuracy improved from on the OfficeCaltech10 (91.8% to 96.85%), OfficeHome (67.7% to 68.10%), Office31 (88.17% to 88.92%), IMAGECLEF-DA (87.9% to 90.24%), PACS (69.08% to 85.72%), and VisDA-2017 (80.2 % to 89.43%) datasets, respectively.INDEX TERMS Domain adaptation, noisy labels, optimal transport, sub-domain adaptation. I. INTRODUCTIONRecently, deep learning models have been bellowing in performance in diverse applications. However, it needs a massive quantity of annotated data for training. Getting labeled data and labeling is too expensive and time-consuming in The associate editor coordinating the review of this manuscript and approving it for publication was Rongbo Zhu . real-world applications. Also, traditional machine learning assumes that training and testing come from identical distributions (I.I.D). In real-world cases, these assumptions may fail because training and testing data may be drawn from different distributions due to domain shifts. For instance, domain shifts may occur by different factors like background clutter, viewpoint, camera quality, environment, dataset bias, etc. Training the model directly the model in the presence of

show abstract

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

Cited by 5 publications

References 33 publications

CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect

CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect

Subdomain adaptation via correlation alignment with entropy minimization for unsupervised domain adaptation

RDAOT: Robust Unsupervised Deep Sub-Domain Adaptation Through Optimal Transport for Image Classification

Contact Info

Product

Resources

About