Target self-guided framework for unsupervised domain adaptation

Modeling patient disease progression using their historical Electronic Health Records (EHRs) is critical to assist clinical decision making and provide prompt medications. Long-Short Term Memory (LSTM) has been widely applied to handle large-scale sequential data such as EHRs. However, when applied to EHRs, the standard LSTM encounters one major limitation: lack of the generalizability given the intricate heterogeneity among different patient groups. To overcome this limitation, we propose a domain adaptation (DA) framework named Time-aware Adversarial Networks, which combines two temporal LSTM-based recurrent components, a label predictor and a domain classifier, to extract an invariant feature representation across different patient groups (domains) through an adversarial learning process. The label predictor learns the temporal developing patterns of the disease while the domain classifier identifies the temporal changes of feature distributions across patient groups. We evaluate the proposed DA framework on modeling the progression of an extremely challenging disease, septic shock, by using real-world EHRs among different patient groups across age, race, and gender. Our results demonstrate that our proposed DA framework can significantly improve the performance for the disease progression modeling while standard machine learning models are severely impacted by the data heterogeneity in EHRs.

A unified framework for visual domain adaptation with covariance matching

Deep learning models have obtained state-of-the-art results for medical image analysis. However, CNNs require a massive amount of labelled data to achieve a high performance. Moreover, many supervised learning approaches assume that the training/source dataset and test/target dataset follow the same probability distribution. Nevertheless, this assumption is hardly satisfied in real-world data and when the models are tested on an unseen domain there is a significant performance degradation. In this work, we present an unsupervised Cross-Modality Adversarial Domain Adaptation (C-MADA) framework for medical image segmentation. C-MADA implements an image-level and feature-level adaptation method in a two-step sequential manner. First, images from the source domain are translated to the target domain through an unpaired image-to-image adversarial translation with cycle-consistency loss. Then, a U-Net network is trained with the mapped source domain images and target domain images in an adversarial manner to learn domain-invariant feature representations and produce segmentations for the target domain. Furthermore, to improve the network’s segmentation performance, information about the shape, texture, and contour of the predicted segmentation is included during the adversarial training. C-MADA is tested on the task of brain MRI segmentation from the crossMoDa Grand Challenge and is ranked within the top 15 submissions of the challenge.

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available for the target domain. While ADDA has already achieved better training efficiency and competitive accuracy on image classification in comparison to other adversarial based methods, we investigate whether we can improve its performance with a new framework and new loss formulations. Following the framework of semi-supervised GANs, we first extend the discriminator output over the source classes, in order to model the joint distribution over domain and task. We thus leverage on the distribution over the source encoder posteriors (which is fixed during adversarial training) and propose maximum mean discrepancy (MMD) and reconstruction-based loss functions for aligning the target encoder distribution to the source domain. We compare and provide a comprehensive analysis of how our framework and loss formulations extend over simple multi-class extensions of ADDA and other discriminative variants of semi-supervised GANs. In addition, we introduce various forms of regularization for stabilizing training, including treating the discriminator as a denoising autoencoder and regularizing the target encoder with source examples to reduce overfitting under a contraction mapping (i.e., when the target per-class distributions are contracting during alignment with the source). Finally, we validate our framework on standard datasets like MNIST, USPS, SVHN, MNIST-M and Office-31. We additionally examine how the proposed framework benefits recognition problems based on sensing modalities that lack training data. This is realized by introducing and evaluating on a neuromorphic vision sensing (NVS) sign language recognition dataset, where the source domain constitutes emulated neuromorphic spike events converted from conventional pixel-based video and the target domain is experimental (real) spike events from an NVS camera. Our results on all datasets show that our proposal is both simple and efficient, as it competes or outperforms the state-of-the-art in unsupervised domain adaptation, such as DIFA and MCDDA, whilst offering lower complexity than other recent adversarial methods.

A simplification–translation–restoration framework for domain adaptation in statistical machine translation: A case study in medical record translation

Accurate segmentation of the optic disc and cup (OD/OC) in fundus images is crucial for the glaucoma diagnosis and treatment. However, the distribution discrepancies (domain shift) between source domain and target domain hinder the generalization of segmentation models in clinical applications. In this paper, a dual gradient alignment framework (DGDA) for unsupervised domain adaptation is proposed to achieve accurate OD/OC segmentation. Specifically, feature gradient alignment module is well-designed to learn the domain-invariant representation by aligning the feature gradients between source and target domains. Furthermore, task gradient alignment module introduces the meta-learning to learn the task-agnostic representation to simultaneously balance domain adaptation and OD/OC segmentation. Here, meta-learning imitates multi-task training by aligning the gradients between the segmentation and domain classification task. Extensive experiments are conducted on the two public fundus image datasets (Drishti-GS and RIM-ONE-r3) to evaluate the effectiveness of the proposed DGDA. Experimental results demonstrate the DGDA successfully achieves the unsupervised domain adaptive OD/OC segmentation with competitive performance compared with the state-of-the-art.

Target-oriented augmentation privacy-protection domain adaptation for imbalanced ECG beat classification

This study proposes a novel self‐training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo‐labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U‐Net showed performance improvements of 0.0588 and 0.1501, respectively, after domain adaptation. Furthermore, the integration of Stable Diffusion for few‐shot image generation enhances domain adaptation performance by 0.0332. The proposed framework enables high‐precision crack segmentation with as few as 100 target images, which can be easily obtained at the site, reducing the cost of model deployment in infrastructure maintenance. The study also investigates the optimal number of iterations for domain adaptation based on the uncertainty score, providing insights for practical implementation. The proposed method contributes to the development of efficient and automated structural health monitoring using AI.

Unsupervised domain adaptation (UDA) has emerged as an effective paradigm for reducing the huge manual annotation cost for Person Re-Identification (Re-ID). Many of the recent UDA methods for Re-ID are clustering-based and select all the pseudo-label samples in each iteration for the model training. However, there are many wrong labeled samples that will mislead the model optimization under this circumstance. To solve this problem, we propose a Progressive Unsupervised Domain Adaptation (PUDA) framework for image-based Person Re-ID to reduce the negative effect of wrong pseudo-label samples on the model training process. Specifically, we first pretrain a CNN model on a labeled source dataset, then finetune the model on unlabeled target dataset with the following three steps iteratively: 1) estimating pseudo-labels for all the images in the target dataset with the model trained in the last iteration; 2) extending the training set by adding pseudo-label samples with higher label confidence; 3) updating the CNN model with the expanded training set in a supervised manner. During the iteration process, the number of pseudo-label samples added increased progressively. In particular, a Moderate Initial Selections (MIS) strategy for pseudo-label sampling is also proposed to reduce the negative impacts of random noise features in the early iterations and mislabeled samples in the late iterations on the model. The proposed framework with MIS strategy is validated on the Duke-to-Market, Market-to-Duke unsupervised domain adaptation tasks and achieves improvements of 4.2 points (absolute, i.e., 80.0% vs. 75.8%) and 1.7 points (absolute, i.e., 70.7% vs. 69.0%) in mAP correspondingly.

Optimal transport (OT) can be applied to cross-domain adaptation in speaker verification (SV) by converting speakers' probability distributions from source to target domains. However, in scenarios involving over-massive categories (speakers) or difficult samples in discrimination, OT often has difficulty computing effective transports. To address this challenge, we propose an OT-based unsupervised domain adaptation (UDA) framework for SV, OT with a diversified memory bank, called DMB-OT, which ensures the accuracy of transfers by two strategies: (1) It regularizes the solution space of OT, which attempts to plan transformations between audio samples from the same speaker with high confidence; (2) it integrates a dynamic curriculum learning algorithm, preventing OT from calculating transport couplings based on hard-discriminative samples in the early stage of UDA. Experiments under different target domains showed that our unsupervised DMB-OT could significantly improve the performance of OT-based UDA and could even match the performance of the supervised PLDA-based adaptation.

In an e-commerce business, the ability to parse postal addresses into sub-component entities (such as building, locality) is essential to take automated actions at scale for successful delivery of shipments. The entities can be leveraged to build applications for logistics related operations, e.g. geocoding, assessing address completeness. Training an accurate address parser requires a significant number of manually labeled examples which is very expensive to create, especially when trying to build model(s) for multiple countries with unique address structure. To tackle this problem, in this paper, we present a novel Unsupervised Domain Adaptation (UDA) framework to transfer knowledge acquired by training a parser on labeled data from one country (source domain) to another (target domain) with unlabeled data. We specifically propose a multi-task student-teacher model comprising of three components: 1) specialized teachers trained on source data to create a pseudo labeled dataset, 2) consistency regularization, that uses a new data augmentation technique for sequence tagging data, and 3) boundary detection, leveraging signals in addresses like commas and text box boundaries. Multiple experiments on diverse address datasets (In this paper, we do not reveal the name of the e-commerce countries on which we evaluate our models due to business confidentiality. We also mask finer address details with (XX) to preserve customer’s privacy.) demonstrate that our approach outperforms state-of-the-art UDA baselines for Named Entity Recognition (NER) task in terms of F1-score by 2–9%.

FTAN: Feature Transform and Alignment Network for cross-domain specific emitter identification

The aim of steganography detection is to identify whether the multimedia data contain hidden information. Although many detection algorithms have been presented to solve tasks with inconsistent distributions between the source and target domains, effectively exploiting transferable correlation information across domains remains challenging. As a solution, we present a novel multiperspective progressive structure adaptation (MPSA) scheme based on active progressive learning (APL) for JPEG steganography detection across domains. First, the source and target data originating from unprocessed steganalysis features are clustered together to explore the structures in different domains, where the intradomain and interdomain structures can be captured to provide adequate information for cross-domain steganography detection. Second, the structure vectors containing the global and local modalities are exploited to reduce nonlinear distribution discrepancy based on APL in the latent representation space. In this way, the signal-to-noise ratio (SNR) of a weak stego signal can be improved by selecting suitable objects and adjusting the learning sequence. Third, the structure adaptation across multiple domains is achieved by the constraints for iterative optimization to promote the discrimination and transferability of structure knowledge. In addition, a unified framework for single-source domain adaptation (SSDA) and multiple-source domain adaptation (MSDA) in mismatched steganalysis can enhance the model's capability to avoid a potential negative transfer. Extensive experiments on various benchmark cross-domain steganography detection tasks show the superiority of the proposed approach over the state-of-the-art methods.

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. First, they mainly align marginal distribution by unsupervised cross-domain feature matching, and ignore each feature's categorical and positional information that can be exploited for conditional alignment; Second, they treat all classes as equally important for transferring cross-domain knowledge and ignore that different classes usually have different transferability. In this article, we propose a joint adaptive detection framework (JADF) to address the above challenges. First, an end-to-end joint adversarial adaptation framework for object detection is proposed, which aligns both marginal and conditional distributions between domains without introducing any extra hyper-parameter. Next, to consider the transferability of each object class, a metric for class-wise transferability assessment is proposed, which is incorporated into the JADF objective for domain adaptation. Further, an extended study from unsupervised domain adaptation (UDA) to unsupervised few-shot domain adaptation (UFDA) is conducted, where only a few unlabeled training images are available in unlabeled target domain. Extensive experiments validate that JADF is effective in both the UDA and UFDA settings, achieving significant performance gains over existing state-of-the-art cross-domain detection methods.

Accurate gearbox fault diagnosis under varying operational speeds is critical for industrial predictive maintenance. A significant challenge is domain shift, where models trained under one condition fail to generalize to another, especially when only healthy data from the target domain is available for training. This study proposes a novel domain adaptation framework, CDANet, that directly leverages raw sensor data to perform multi-class fault classification without manual feature engineering. The model combines a lightweight CNNbased temporal feature extractor with a frozen DistilBERT encoder to capture transferable, domain-invariant representations, combined with a maximum mean discrepancy loss to align the feature distributions between the source and target domains using only healthy samples. Experimental results demonstrate that our proposed model significantly outperforms conventional deep learning approaches, achieving high classification accuracy across six domain adaptation tasks. This work validates the effectiveness of applying pre-trained models in domain adaptation for gearbox fault diagnosis under real-world domain shift constraints.