Inter-class distribution alienation and inter-domain distribution alignment based on manifold embedding for domain adaptation

Domain adaptation (DA) aims to train a robust predictor by transferring rich knowledge from a well-labeled source domain to annotate a newly coming target domain; however, the two domains are usually drawn from very different distributions. Most current methods either learn the common features by matching inter-domain feature distributions and training the classifier separately or align inter-domain label distributions to directly obtain an adaptive classifier based on the original features despite feature distortion. Moreover, intra-domain information may be greatly degraded during the DA process; i.e., the source data samples from different classes might grow closer. To this end, this paper proposes a novel DA approach, referred to as inter-class distribution alienation and inter-domain distribution alignment based on manifold embedding (IDAME). Specifically, IDAME commits to adapting the classifier on the Grassmann manifold by using structural risk minimization, where inter-domain feature distributions are aligned to mitigate feature distortion, and the target pseudo labels are exploited using the distances on the Grassmann manifold. During the classifier adaptation process, we simultaneously consider the inter-class distribution alienation, the inter-domain distribution alignment, and the manifold consistency. Extensive experiments validate that IDAME can outperform several comparative state-of-the-art methods on real-world cross-domain image datasets.

One-Dimensional Multi-Scale Domain Adaptive Network for Bearing-Fault Diagnosis under Varying Working Conditions

Data-driven bearing-fault diagnosis methods have become a research hotspot recently. These methods have to meet two premises: (1) the distributions of the data to be tested and the training data are the same; (2) there are a large number of high-quality labeled data. However, machines usually work under different working conditions in practice, which challenges these prerequisites due to the fact that the data distributions under different working conditions are different. In this paper, the one-dimensional Multi-Scale Domain Adaptive Network (1D-MSDAN) is proposed to address this issue. The 1D-MSDAN is a kind of deep transfer model, which uses both feature adaptation and classifier adaptation to guide the multi-scale convolutional neural network to perform bearing-fault diagnosis under varying working conditions. Feature adaptation is performed by both multi-scale feature adaptation and multi-level feature adaptation, which helps in finding domain-invariant features by minimizing the distribution discrepancy between different working conditions by using the Multi-kernel Maximum Mean Discrepancy (MK-MMD). Furthermore, classifier adaptation is performed by entropy minimization in the target domain to bridge the source classifier and target classifier to further eliminate domain discrepancy. The Case Western Reserve University (CWRU) bearing database is used to validate the proposed 1D-MSDAN. The experimental results show that the diagnostic accuracy for the 12 transfer tasks performed by 1D-MSDAN was superior to that of the mainstream transfer learning models for bearing-fault diagnosis under variable working conditions. In addition, the transfer learning performance of 1D-MSDAN for multi-target domain adaptation and real industrial scenarios was also verified.

C2DAN: An Improved Deep Adaptation Network with Domain Confusion and Classifier Adaptation

Deep neural networks have been successfully applied in domain adaptation which uses the labeled data of source domain to supplement useful information for target domain. Deep Adaptation Network (DAN) is one of these efficient frameworks, it utilizes Multi-Kernel Maximum Mean Discrepancy (MK-MMD) to align the feature distribution in a reproducing kernel Hilbert space. However, DAN does not perform very well in feature level transfer, and the assumption that source and target domain share classifiers is too strict in different adaptation scenarios. In this paper, we further improve the adaptability of DAN by incorporating Domain Confusion (DC) and Classifier Adaptation (CA). To achieve this, we propose a novel domain adaptation method named C2DAN. Our approach first enables Domain Confusion (DC) by using a domain discriminator for adversarial training. For Classifier Adaptation (CA), a residual block is added to the source domain classifier in order to learn the difference between source classifier and target classifier. Beyond validating our framework on the standard domain adaptation dataset office-31, we also introduce and evaluate on the Comprehensive Cars (CompCars) dataset, and the experiment results demonstrate the effectiveness of the proposed framework C2DAN.

Improving Whole-Brain Neural Decoding of fMRI with Domain Adaptation

In neural decoding, there has been a growing interest in machine learning on whole-brain functional magnetic resonance imaging (fMRI). However, the size discrepancy between the feature space and the training set poses serious challenges. Simply increasing the number of training examples is infeasible and costly. In this paper, we proposed a domain adaptation framework for whole-brain fMRI (DawfMRI) to improve whole-brain neural decoding on target data leveraging pre-existing source data. DawfMRI consists of three steps: 1) feature extraction from whole-brain fMRI, 2) source and target feature adaptation, and 3) source and target classifier adaptation. We evaluated its eight possible variations, including two non-adaptation and six adaptation algorithms, using a collection of seven task-based fMRI datasets (129 unique subjects and 11 cognitive tasks in total) from the OpenNeuro project. The results demonstrated that appropriate source domain can help improve neural decoding accuracy for challenging classification tasks. The best-case improvement is 8.94% (from 78.64% to 87.58%). Moreover, we discovered a plausible relationship between psychological similarity and adaptation effectiveness. Finally, visualizing and interpreting voxel weights showed that the adaptation can provide additional insights into neural decoding.