Domain adaptation under hidden confounding

Before the operation of a biosignal-based application, long-duration calibration is required to adjust the pre-trained classifier to a new user data (target data). For reducing such time-consuming step, linear domain adaptation (DA) transfer learning approaches, which transfer pooled data (source data) related to the target data, are highlighted. In the last decade, they have been applied to surface electromyogram (sEMG) data with the implicit assumption that sEMG data are linear. However, sEMGs typically have non-linear characteristics, and due to the discrepancy between the assumption and actual characteristics, linear DA approaches would cause a negative transfer. This study investigated how the correlation between the source and target data affects an 8-class forearm movement classification after applying linear DA approaches. As a result, we found significant positive correlations between the classification accuracy and the source-target correlation. Additionally, the source-target correlation depended on the motion class. Therefore, our results suggest that we should choose a non-linear DA approach when the source-target correlation among subjects or motion classes is low.

Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to mitigate the performance drop. However, very little attention has been made toward leveraging information in videos which are naturally captured in most camera systems. In this work, we propose to leverage “motion prior” in videos for improving human segmentation in a weakly-supervised active learning setting. By extracting motion information using optical flow in videos, we can extract candidate foreground motion segments (referred to as motion prior) potentially corresponding to human segments. We propose to learn a memory-network-based policy model to select strong candidate segments (referred to as strong motion prior) through reinforcement learning. The selected segments have high precision and are directly used to finetune the model. In a newly collected surveillance camera dataset and a publicly available UrbanStreet dataset, our proposed method improves the performance of human segmentation across multiple scenes and modalities (i.e., RGB to Infrared (IR)). Last but not least, our method is empirically complementary to existing domain adaptation approaches such that additional performance gain is achieved by combining our weakly-supervised active learning approach with domain adaptation approaches.

Summary Introduction : There has been a rapid development of deep learning (DL) models for medical imaging. However, DL requires a large labeled dataset for training the models. Getting large-scale labeled data remains a challenge, and multi-center datasets suffer from heterogeneity due to patient diversity and varying imaging protocols. Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space. DA is a type of transfer learning (TL) that can improve the performance of models when applied to multiple different datasets. Objective : In this survey, we review the state-of-the-art DL-based DA methods for medical imaging. We aim to summarize recent advances, highlighting the motivation, challenges, and opportunities, and to discuss promising directions for future work in DA for medical imaging. Methods : We surveyed peer-reviewed publications from leading biomedical journals and conferences between 2017-2020, that reported the use of DA in medical imaging applications, grouping them by methodology, image modality, and learning scenarios. Results : We mainly focused on pathology and radiology as application areas. Among various DA approaches, we discussed domain transformation (DT) and latent feature-space transformation (LFST). We highlighted the role of unsupervised DA in image segmentation and described opportunities for future development. Conclusion : DA has emerged as a promising solution to deal with the lack of annotated training data. Using adversarial techniques, unsupervised DA has achieved good performance, especially for segmentation tasks. Opportunities include domain transferability, multi-modal DA, and applications that benefit from synthetic data.

Machine learning (ML) is increasingly applied in optical network management, especially in cross-layer frameworks where physical layer characteristics may trigger changes at the network layer due to transmission performance measurements (quality of transmission, QoT) monitored by optical equipment. Leveraging ML-based QoT estimation approaches has proven to be a promising alternative to exploiting classical mathematical methods or transmission simulation tools. However, supervised ML models rely on large representative training sets, which are often unavailable, due to the lack of the necessary telemetry equipment or of historical data. In such cases, it can be useful to use training data collected from a different network. Unfortunately, the resulting models may be uneffective when applied to the current network, if the training data (the source domain) is not well representative of the network under study (the target domain). Domain adaptation (DA) techniques aim at tackling this issue, to make possible the transfer of knowledge among different networks. This paper compares several DA approaches applied to the problem of estimating the QoT of an optical lightpath using a supervised ML approach. Results show that, when the number of samples from the target domain is limited to a few dozen, DA approaches consistently outperform standard supervised ML techniques.

Multi-target domain adaptation intelligent diagnosis method for rotating machinery based on multi-source attention mechanism and mixup feature augmentation

An unsupervised domain adaptation brain CT segmentation method across image modalities and diseases

Domain adaptation investigates the problem of leveraging knowledge from a well-labeled source domain to an unlabeled target domain, where the two domains are drawn from different data distributions. Because of the distribution shifts, different target samples have distinct degrees of difficulty in adaptation. However, existing domain adaptation approaches overwhelmingly neglect the degrees of difficulty and deploy exactly the same framework for all of the target samples. Generally, a simple or shadow framework is fast but rough. A sophisticated or deep framework, on the contrary, is accurate but slow. In this paper, we aim to challenge the fundamental contradiction between the accuracy and speed in domain adaptation tasks. We propose a novel approach, named agile domain adaptation, which agilely applies optimal frameworks to different target samples and classifies the target samples according to their adaptation difficulties. Specifically, we propose a paradigm which performs several early detections before the final classification. If a sample can be classified at one of the early stage with enough confidence, the sample would exit without the subsequent processes. Notably, the proposed method can significantly reduce the running cost of domain adaptation approaches, which can extend the application scenarios of domain adaptation to even mobile devices and real-time systems. Extensive experiments on two open benchmarks verify the effectiveness and efficiency of the proposed method.

Domain Adaptation (DA) has attracted a lot of attention in recent years. DA aims at overcoming the covariate shift in dataset and aligning multiple existing but partially related data collections. In this paper, we propose a new DA algorithm which aligns the weighted subspaces generated from source samples and target samples. The weighted subspaces of source samples are generated using weighted Principal Component Analysis (PCA). Specifically, the source samples closer to the target domain are given higher weights during the construction of subspaces, which is definitely beneficial for building an adaptable classifier. Subsequently, the weighted subspaces of source samples and the subspaces of target samples are aligned to achieve domain adaptation. Experimental results on standard datasets demonstrate the advantages of our approach over state-of-the-art DA approaches.

In real-world hyperspectral image (HSI) classification, the limited annotated examples usually lead to the insufficiently trained classifier, which further generates low classification accuracy. To overcome this challenge, Domain Adaptation (DA) methods have been developed to transfer learnable knowledge from the external HSIs with sufficient labeled examples ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., the source domain) to the interested HSI with scarce labeled examples ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., the target domain). Conventional DA approaches often pseudo-label the examples with high classification confidence and then incorporate them in the training process. However, due to the significant domain gap, relying solely on the confident examples may not be adequate to achieve satisfactory performance. Therefore, this paper proposes an Interactive Easy-to-Hard Domain Adaptation method (IEH-DA) to arrange the adaptation process so that the “easy” examples are adapted ahead of the “hard” ones. In an early stage, the easy examples with high pseudo-labeling confidence are selected for the adversarial learning based DA. In a later stage, the “hard” examples with high informativity are further selected, and they are interactively labeled by human expert to provide accurate supervision information for adaptation. As a result, the examples in target domain are used in an easy-to-hard way, which forms a curriculum sequence for orderly model training. Extensive experiments conducted on typical public datasets demonstrate that IEH-DA outperforms other state-of-the-art DA methods for HSI classification.

Remaining useful life (RUL) prediction is one of the core issues in the equipment maintenance process. It aims to accurately forecast machines’ run-to-failure life span using previous and current state data. As various data-driven models are proving to be effective, because RUL labels for machines in particular conditions are difficult to obtain, domain adaptation approaches begins to be explored in the RUL prediction issue. We propose a novel Dual Mix-up Adversarial Domain Adaptation (DMADA) approach to further improve the RUL forecasting accuracy, building on existing RUL domain adaptation studies. In DMADA, both time-series mix-up and domain mix-up regularization are conducted. Virtual samples generated by linear interpolation lead to enriched and more continuous sample space. The linear interpolation encourages consistency of prediction in-between samples and allows the model to explore the feature space more thoroughly. At the same time, the domain mixup conserves the invariance of learned features. The two mixup regularizations combined promote both the transferability and the discriminability of extracted features, which is essential to satisfactory unsupervised domain adaptation performance. Thorough experiments on the C-MPASS dataset are conducted and satisfactory results prove the proposed approach effective.

The concept of transfer learning has received a great deal of concern and interest throughout the last decade. Selecting an ideal representational framework for instances of various domains to minimize the divergence among source and target domains is a fundamental research challenge in representative transfer learning. The domain adaptation approach is designed to learn more robust or higher-level features, required in transfer learning. This paper presents a novel transfer learning framework that employs a marginal probability-based domain adaptation methodology followed by a deep autoencoder. The proposed frame adapts the source and target domain by plummeting distribution deviation between the features of both domains. Further, we adopt the deep neural network process to transfer learning and suggest a supervised learning algorithm based on encoding and decoding layer architecture. Moreover, we have proposed two different variants of the transfer learning techniques for classification, which are termed as (i) Domain adapted transfer learning with deep autoencoder-1 (D-TLDA-1) using the linear regression and (ii) Domain adapted transfer learning with deep autoencoder-2 (D-TLDA-2) using softmax regression. Simulations have been conducted with two popular real-world datasets: ImageNet datasets for image classification problem and 20_Newsgroups datasets for text classification problem. Experimental findings have established and the resulting improvements in accuracy measure of classification shows the supremacy of the proposed D-TLDA framework over prominent state-of-the-art machine learning and transfer learning approaches.

The age determination of fish is fundamental to marine resource management. This task is commonly done by analysis of otoliths performed manually by human experts. Otolith images from Greenland halibut acquired by the Institute of Marine Research (Norway) were recently used to train a convolutional neural network (CNN) for automatically predicting fish age, opening the way for requiring less human effort and availability of expertise by means of deep learning (DL). In this study, we demonstrate that applying a CNN model trained on images from one lab (in Norway) does not lead to a suitable performance when predicting fish ages from otolith images from another lab (in Iceland) for the same species. This is due to a problem known as dataset shift, where the source data, i.e., the dataset the model was trained on have different characteristics from the dataset at test stage, here denoted as target data. We further demonstrate that we can handle this problem by using domain adaptation, such that an existing model trained in the source domain is adapted to perform well in the target domain, without requiring extra annotation effort. We investigate four different approaches: (i) simple adaptation via image standardization, (ii) adversarial generative adaptation, (iii) adversarial discriminative adaptation and (iv) self-supervised adaptation. The results show that the performance varies substantially between the methods, with adversarial discriminative and self-supervised adaptations being the best approaches. Without using a domain adaptation approach, the root mean squared error (RMSE) and coefficient of variation (CV) on the Icelandic dataset are as high as 5.12 years and 28.6%, respectively, whereas by using the self-supervised domain adaptation, the RMSE and CV are reduced to 1.94 years and 11.1%. We conclude that careful consideration must be given before DL-based predictors are applied to perform large scale inference. Despite that, domain adaptation is a promising solution for handling problems of dataset shift across image labs.

Although Deep Convolutional Neural Network (DCNN) has been admittedly witnessed as an enormous success in a wide range of applications, most of them require sufficient annotations with time-consuming and labor-exhausting efforts. Existing domain adaptation (DA) approaches delve into designing an effective loss module to minimize the distribution gap between the source and target domains. However, few studies pay attention to improve the backbone or network architecture for DA issues. In this paper, we propose a new backbone for DA specially, i.e., Transferable ResNet (TransResNet). TransResNet remedies the residual block in ResNet, separating source and target input features and highlighting more transferable channels in each block. It can be easily applied to all kinds of DA methods, without adding any extra learning parameters. We conduct substantial experiments on two general DA datasets and embed TransResNet into two seminal DA methods, including DANN and CDAN. Experimental results demonstrate TransResNet improves the transferability of the architecture, indicating that it is a great substitute for ResNet as a network backbone in DA issues.

Robust and reliable drivetrain is important for preventing electromechanical (e.g., wind turbine) downtime. In recent years, advanced machine learning (ML) techniques including deep learning have been introduced to improve fault diagnosis performance for electromechanical systems. However, electromechanical systems (e.g., wind turbine) operate in varying working conditions, meaning that the distribution of the test data (in the target domain) is different from the training data used for model training, and the diagnosis performance of an ML method may become downgraded for practical applications. This paper proposes a joint distribution optimal deep domain adaptation approach (called JDDA) based auto-encoder deep classifier for fault diagnosis of electromechanical drivetrains under the varying working conditions. First, the representative features are extracted by the deep auto-encoder. Then, the joint distribution adaptation is used to implement the domain adaptation, so the classifier trained with the source domain features can be used to classify the target domain data. Lastly, the classification performance of the proposed JDDA is tested using two test-rig datasets, compared with three traditional machine learning methods and two domain adaptation approaches. Experimental results show that the JDDA can achieve better performance compared with the reference machine learning, deep learning and domain adaptation approaches.

Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. Existing DA normally assumes the well-labeled source domain is class-wise balanced, which means the size per source class is relatively similar. However, in real-world applications, labeled samples for some categories in the source domain could be extremely few due to the difficulty of data collection and annotation, which leads to decreasing performance over target domain on those few-shot categories. 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 facilitate the target learning. Experimental results on two large cross-domain visual datasets demonstrate the effectiveness of our proposed method on improving both few-shot and overall classification accuracy comparing with the state-of-the-art DA approaches.