Domain Adaptation: Challenges, Methods, Datasets, and Applications

Singhal, Peeyush; Walambe, Rahee; Ramanna, Sheela; Kotecha, Ketan

doi:10.1109/access.2023.3237025

Cited by 37 publications

(16 citation statements)

References 297 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ben et al delved deeper into the reasons why networks trained on simulated data using conventional methods are unlikely to exhibit generalized performance on real tissue [ 51 ]. Domain adaptation is a sub case of transfer learning developed in the field of computer vision [ 52 , 53 , 54 ], aiming to leverage the related source domain to learn unseen features in the target domain. To be more specific, unsupervised learning techniques can be deployed for the above domain adaptation task without the need of paired images.…”

Section: Discussionmentioning

confidence: 99%

Mitigating Under-Sampling Artifacts in 3D Photoacoustic Imaging Using Res-UNet Based on Digital Breast Phantom

Huo,

Deng,

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, photoacoustic (PA) imaging has rapidly grown as a non-invasive screening technique for breast cancer detection using three-dimensional (3D) hemispherical arrays due to their large field of view. However, the development of breast imaging systems is hindered by a lack of patients and ground truth samples, as well as under-sampling problems caused by high costs. Most research related to solving these problems in the PA field were based on 2D transducer arrays or simple regular shape phantoms for 3D transducer arrays or images from other modalities. Therefore, we demonstrate an effective method for removing under-sampling artifacts based on deep neural network (DNN) to reconstruct high-quality PA images using numerical digital breast simulations. We constructed 3D digital breast phantoms based on human anatomical structures and physical properties, which were then subjected to 3D Monte-Carlo and K-wave acoustic simulations to mimic acoustic propagation for hemispherical transducer arrays. Finally, we applied a 3D delay-and-sum reconstruction algorithm and a Res-UNet network to achieve higher resolution on sparsely-sampled data. Our results indicate that when using a 757 nm laser with uniform intensity distribution illuminated on a numerical digital breast, the imaging depth can reach 3 cm with 0.25 mm spatial resolution. In addition, the proposed DNN can significantly enhance image quality by up to 78.4%, as measured by MS-SSIM, and reduce background artifacts by up to 19.0%, as measured by PSNR, even at an under-sampling ratio of 10%. The post-processing time for these improvements is only 0.6 s. This paper suggests a new 3D real time DNN method addressing the sparse sampling problem based on numerical digital breast simulations, this approach can also be applied to clinical data and accelerate the development of 3D photoacoustic hemispherical transducer arrays for early breast cancer diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Mitigating Under-Sampling Artifacts in 3D Photoacoustic Imaging Using Res-UNet Based on Digital Breast Phantom

Huo,

Deng,

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Cross-domain classification also plays an important role in extending the fruits of the data-hungry deep models to be reaped for data-scarce applications by adapting the models trained using large amounts of other related data to work on the scarce data sampled from a different distribution. Specifically, domain adaptation refers to the process of adapting a model trained on a data-rich source domain to a data-scarce target domain where the distributions of the data may be different [18,19]. In this context, explainability can help understand how the model adapts to the differences in the source and target domains.…”

Section: Explaining Cross-domain Classificationmentioning

confidence: 99%

“…However, collecting extensive labeled data is challenging in real-world scenarios. To leverage the power of deep models in data-sparse scenarios, cross-domain classification paradigms [18,19] have emerged, where the model is expected to handle the distribution from which the sparse data is sampled, leveraging knowledge acquired from publicly available voluminous data sampled from a different distribution. This phenomenon, a crucial factor in the widespread adoption of deep models, necessitates explanation, and initial efforts [20,21] have been made in this direction.…”

Section: Introductionmentioning

confidence: 99%

Explainable Image Classification: The Journey So Far and the Road Ahead

Kamakshi,

Krishnan

2023

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address the interpretability challenges posed by complex machine learning models. In this survey paper, we provide a comprehensive analysis of existing approaches in the field of XAI, focusing on the tradeoff between model accuracy and interpretability. Motivated by the need to address this tradeoff, we conduct an extensive review of the literature, presenting a multi-view taxonomy that offers a new perspective on XAI methodologies. We analyze various sub-categories of XAI methods, considering their strengths, weaknesses, and practical challenges. Moreover, we explore causal relationships in model explanations and discuss approaches dedicated to explaining cross-domain classifiers. The latter is particularly important in scenarios where training and test data are sampled from different distributions. Drawing insights from our analysis, we propose future research directions, including exploring explainable allied learning paradigms, developing evaluation metrics for both traditionally trained and allied learning-based classifiers, and applying neural architectural search techniques to minimize the accuracy–interpretability tradeoff. This survey paper provides a comprehensive overview of the state-of-the-art in XAI, serving as a valuable resource for researchers and practitioners interested in understanding and advancing the field.

show abstract

“…Before delving into the details of DA, we introduce essential notations and definitions derived from survey works [ 19 , 20 ]. A domain is defined as a distribution

, represented as

, where

denotes the input feature and

denotes a marginal probability distribution.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…DA methods can be categorized based on their approach to transferring knowledge from source to target domains. A comprehensive review by Singhal et al [ 19 ] classified DA methods into three categories: feature-based and two data-based DA methods. Feature-based DA methods aim to learn a domain-invariant feature representation by minimizing data distribution discrepancies between domains.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Weighted Domain Adaptation Using the Graph-Structured Dataset Representation for Machinery Fault Diagnosis under Varying Operating Conditions

Choi,

Kong,

Cho

2023

Sensors

View full text Add to dashboard Cite

Data-driven fault diagnosis has received significant attention in the era of big data. Most data-driven methods have been developed under the assumption that both training and test data come from identical data distributions. However, in real-world industrial scenarios, data distribution often changes due to varying operating conditions, leading to a degradation of diagnostic performance. Although several domain adaptation methods have shown their feasibility, existing methods have overlooked metadata from the manufacturing process and treated all domains uniformly. To address these limitations, this article proposes a weighted domain adaptation method using a graph-structured dataset representation. Our framework involves encoding a collection of datasets into the proposed graph structure, which captures relations between datasets based on metadata and raw data simultaneously. Then, transferability scores of candidate source datasets for a target are estimated using the constructed graph and a graph embedding model. Finally, the fault diagnosis model is established with a voting ensemble of the base classifiers trained on candidate source datasets and their estimated transferability scores. For validation, two case studies on rotor machinery, specifically tool wear and bearing fault detection, were conducted. The experimental results demonstrate the effectiveness and superiority of the proposed method over other existing domain adaptation methods.

show abstract

Domain Adaptation: Challenges, Methods, Datasets, and Applications

Cited by 37 publications

References 297 publications

Mitigating Under-Sampling Artifacts in 3D Photoacoustic Imaging Using Res-UNet Based on Digital Breast Phantom

Mitigating Under-Sampling Artifacts in 3D Photoacoustic Imaging Using Res-UNet Based on Digital Breast Phantom

Explainable Image Classification: The Journey So Far and the Road Ahead

Weighted Domain Adaptation Using the Graph-Structured Dataset Representation for Machinery Fault Diagnosis under Varying Operating Conditions

Contact Info

Product

Resources

About