Domain Alignment Research Articles

DW-D3A: dynamic weighted dual-driven domain adaptation for cross-scene hyperspectral image classification

ABSTRACT Domain adaptation (DA) offers an effective way to align feature distributions of the source domain (SD) and the target domain (TD) without requiring any target label samples. As a method of DA, representation learning effectively realizes the alignment of feature distributions in different domains by transferring domain knowledge. However, existing representation learning methods often focus on unilateral representation transfer, which potentially results in transfer bias. Additionally, most methods ignore the connection between domain alignment and discrimination during the DA process, which easily causes negative transfer. This paper proposes a dynamic weighted dual-driven domain adaptation (DW-D 3 A) model that effectively addresses the aforementioned issues through bilateral feature transfer between domains and a dynamic weighted scheme. Technically, we first propose a dual-driven domain adaptation (D 3 A) model, which employs symmetrical structures to facilitate the knowledge transfer of bilateral representations between source and target domain samples, learning the subspaces of two domains and reducing distribution discrepancies between subspaces via joint distribution-driven alignment. This process mitigates transfer bias and goes beyond previous unilateral transfer methods. Then, to alleviate strong constraints on projecting SD and TD into the same subspace in existing approaches, we apply a relaxed subspace constraint to bring the projections of SD and TD closer. Furthermore, data reconstruction is incorporated to preserve discriminant information from the original data. Lastly, we expand (D 3 A) to DW-D 3 A using a dynamic weighted scheme, which adjusts the weights assigned to domain alignment and discrimination based on their significance to inhibit negative transfer. Extensive experimentation on three datasets indicates that DW-D 3 A outperforms seven other DA methods, showing its superior performance.

Cross-Domain Feature Disentanglement for Interpretable Modeling of Tumor Microenvironment Impact on Drug Response.

High-throughput screening technology has enabled the generation of large-scale drug responses across hundreds of cancer cell lines. There remains a significant gap between in vitro cell lines and actual tumors in vivo in terms of their response to drug treatments yet. This is because tumors consist of a complex cellular composition and histopathology structure, known as the tumor microenvironment (TME), which greatly impacts the drug cytotoxicity against tumor cells. To date, no study has focused on modeling the impact of the TME on clinical drug response. In this study, we postulated that the intricate complexity of an actual tumor can be conceptually simplified into two separable components: cancerous cells and the tumor microenvironment. This assumption allowed us to model the influence of these two constituent parts on drug response through feature disentanglement. We employed a domain adaptation network to decouple and extract features from tumor transcriptional profiles. Specifically, two denoising autoencoders were separately used to extract features from cell lines (source domain) and tumors (target domain) for partial domain alignment and feature decoupling. The private encoder was enforced to extract information only about the TME. Moreover, to ensure generalizability to novel drugs, we employed a graph attention network to learn the latent representation of drugs, enabling us to linearly model the drug perturbation on cellular state in latent space. We validated our model on a benchmark dataset and demonstrated its superior performance in predicting clinical drug response and dissecting the influence of the TME on drug efficacy.

Global semantics correlation transmitting and learning for sketch-based cross-domain visual retrieval

Sketch-based cross-domain visual data retrieval is the process of searching for images or 3D models using sketches as input. Achieving feature alignment is a significantly challenging task due to the high heterogeneity of cross-domain data. However, the alignment process faces significant challenges, such as domain gap, semantic gap, and knowledge gap. The existing methods adopt different ideas for sketch-based image and 3D shape retrieval tasks, one is domain alignment, and the other is semantic alignment. Technically, both tasks verify the accuracy of extracted features. Hence, we propose a method based on the global feature correlation and the feature similarity for multiple sketch-based cross-domain retrieval tasks. Specifically, the data from various modalities are fed into separate feature extractors to generate original features. Then, these features are projected to the shared subspace. Finally, domain consistency learning, semantic consistency learning, feature correlation learning and feature similarity learning are performed jointly to make the projected features modality-invariance. We evaluate our method on multiple benchmark datasets. Where the MAP in Sketchy, TU-Berlin, SHREC 2013 and SHREC 2014 are 0.466, 0.473, 0.860 and 0.816. The extensive experimental results demonstrate the superiority and generalization of the proposed method, compared to the state-of-the-art approaches. The in-depth analyses of various design choices are also provided to gain insight into the effectiveness of the proposed method. The outcomes of this research contribute to advancing the field of sketch-based cross-domain visual data retrieval and are expected to be applied to a variety of applications that require efficient retrieval of cross-domain domain data.

Aligning the domains in cross domain model inversion attack

Model Inversion Attack reconstructs confidential training dataset from a target deep learning model. Most of the existing methods assume the adversary has an auxiliary dataset that has similar distribution with the private dataset. However, this assumption does not always hold in real-world scenarios. Since the private dataset is unknown, the domain divergence between the auxiliary dataset and the private dataset is inevitable. In this paper, we use Cross Domain Model Inversion Attack to represent the distribution divergence scenario in MIA. With the distribution divergence between the private images and auxiliary images, the distribution between the feature vectors of the private images and those of the auxiliary images is also different. Moreover, the outputted prediction vectors of the auxiliary images are also misclassified. The inversion attack is thus hard to be performed. We perform both the feature vector inversion task and prediction vector inversion task in this cross domain setting. For feature vector inversion, Domain Alignment MIA (DA-MIA) is proposed. While performing the reconstruction task, DA-MIA aligns the feature vectors of auxiliary images with the feature vectors of private images in an adversarial manner to mitigate the domain divergence between them. Thus, semantically meaningful images can be reconstructed. For prediction vector inversion, we further introduce an auxiliary classifier and propose Domain Alignment MIA with Auxiliary Classifier (DA-MIA-AC). The auxiliary classifier is pretrained by the auxiliary dataset and fine-tuned during the adversarial training stage. Thus, the misclassification problem caused by domain divergence can be solved, and the images can be reconstructed correctly. Various experiments are performed to show the advancement of our methods, the results show that DA-MIA can improve the SSIM score of the reconstructed images for up to 191%, DA-MIA-AC can increase the classification accuracy score of the reconstructed images from 9.18% to 81.32% in Cross Domain Model Inversion Attack.

A new indirect transfer fault diagnosis method based on feature separation

The existing fault diagnosis methods based on deep transfer learning achieve domain adaptation by matching shared features between the source and target domains. However, there are different private characteristics between the source domain and the target domain, and traditional cross-domain fault diagnosis algorithms ignore the impact of private attributes in the target domain on classification tasks. Meanwhile, the existence of private features causes a negative transfer problem for domain adaptation methods in domains with large aligned domain gaps. In practical applications, indirect transfer between the source domain and target domain can reduce the limitations of inherent attributes and enhance the guidance of private features in the target domain for classification tasks, which can enrich the transfer of fault knowledge and improve the effectiveness of cross-domain fault diagnosis. Therefore, an indirect transfer fault diagnosis method based on feature separation (ITFS) is proposed. Firstly, an attention-enhanced feature separation framework is proposed, which constructs a set of joint attention convolutional autoencoders (CAEs) to separate features from two domains, avoiding the influence of domain shift in private features. Secondly, to better adapt the two domains, an indirect domain adaptation method based on Gaussian distribution is proposed, which combines Gaussian indirect transfer learning with pseudo-labeling enhancement to reduce the domain gap in the two domains. Six transfer tasks on the PU datasets demonstrate that compared to MCD, the average accuracy of the proposed method is improved by 14.09 %, and it is superior to other popular existing methods. Experiments on three publicly available datasets have shown that this method outperforms other popular existing methods.

Dumbbell-Shaped, Block-Graft Copolymer with Aligned Domains for High-Performance Hydrocarbon Polymer Electrolyte Membranes.

Given the environmental concerns surrounding fluoromaterials, the use of high-cost perfluorinated sulfonic acids (PFSAs) in fuel cells and water electrolysis contradicts the pursuit of clean energy systems. Herein, we present a fluorine-free dumbbell-shaped block-graft copolymer, derived from the cost-effective triblock copolymer, poly(styrene-b-ethylene-co-butylene-b-styrene) (SEBS), for polymer electrolyte membranes (PEMs). This unique polymer shape led to the alignment of the hydrophobic-hydrophilic domains along a preferred orientation, resulting in the construction of interconnected proton channels across the membrane. A bicontinuous network allowed efficient proton transport with reduced tortuosity, leading to an exceptional ionic conductivity (249 mS cm-1 at 80 °C and 90 % relative humidity (RH)), despite a low ion exchange capacity (IEC; 1.41). Furthermore, membrane electrode assembly (MEA) prepared with our membrane exhibited stable performance over a period of 150 h at 80 °C and 30 % RH. This study demonstrates a novel polymer structure design and highlights a promising outlook for hydrocarbon PEMs as alternatives to PFSAs.

Dynamic simulation-assisted Gaussian mixture alignment approach for fault diagnosis of rotation machinery under small samples

Abstract Obtaining a substantial number of actual samples for rotating machinery in an industrial setting can be challenging, particularly when faulty samples are acquired under hazardous working conditions. The issue of insufficient samples hinders the effective training of reliable fault diagnosis models, impeding the industrial implementation of advanced intelligent methods. This study proposes an innovative dynamic simulation-assisted Gaussian mixture alignment model (DSGMA) to address the challenge of applying fault diagnosis technologies, with its performance mined by advanced transfer algorithms. Specifically, we establish a fault dynamics model for rotating machinery and acquire a substantial amount of simulated data as the source domain to facilitate the training of the deep neural network model. Subsequently, we propose a Gaussian mixture-guided domain alignment approach that assigns a domain-independent Gaussian distribution to each category as prior knowledge, with the parameters calculated using limited actual samples. Diagnostic knowledge is transferred from the source domain to the target domain by minimizing the Kullback–Leibler divergence between the features of the simulated samples and the Gaussian mixture priors. Furthermore, the DSGMA model incorporates Gaussian clustering loss to augment the clustering capability of samples belonging to the same category from real devices and enhances the computational stability of the parameters in the Gaussian mixture model. The efficacy of the DSGMA method is validated using three publicly available datasets and compared against five widely adopted methods. The experimental findings illustrate that DSGMA exhibits superior diagnostic and robust capabilities, facilitating efficient fault diagnosis under scenarios of small samples.

Dual-weight attention-based multi-source multi-stage alignment domain adaptation for industrial fault diagnosis

Abstract Cross-domain fault diagnosis is crucial for industrial applications with various and unknown operating conditions. However, due to the significant differences in the distribution of features in multiple source domains, it may lead to mutual interference of features between different domains and reduce the accuracy of diagnosis, which is a problem not considered by most current researches. In addition, most of the existing methods focus only on the extraction of low-frequency global information and cannot adequately deal with high-frequency local information. Consequently, this paper provides a multi-stage processing integrated dual-weight attention-based multi-source multi-stage aligned domain adaptation (DAMMADA) method. Global fault features that are shared by various subdomains are extracted by three domain-specific feature extractors from various domains. In a local feature extractor, the dual-weight attention module not only uses shared weights to aggregate local information, but it also uses contextual weights to improve local features. In terms of loss handling, multiple pseudo-labels are used to reduce the loss of the local maximum mean discrepancy in order to learn the domain-invariant characteristics after improving the high-frequency and low-frequency information extraction. To modify the classification boundaries, the pseudo-labels’ mean square errors are combined. Comprehensive experiments were carried out on two platforms for fault diagnosis of SCARA robots and bearings respectively, and the results demonstrated that DAMMADA is superior to other methods in terms of accuracy and its ability to suppress negative transfer for cross-domain tasks.

A dynamically class-wise weighting mechanism for unsupervised cross-domain object detection under universal scenarios

In the realm of object detection, traditional domain adaptive object detection (DAOD) methods assume that source and target data completely share one identical class space, which is often difficult to satisfy in many real-world applications. To address this limitation, this paper introduces universal domain adaptive object detection (UniDAOD), a learning paradigm that relaxes identical class space assumption to be a different but overlapped class space. Intuitively, the main challenge of UniDAOD is to reduce the negative transfer of private classes (i.e., classes only existed in one domain) and reinforce the positive transfer of the common classes (i.e., classes shared across domains). In this paper, we provide a rigorous theoretical analysis and induce a new generalization bound of the expected target error under the UniDAOD setting. On the basis of theoretical insight, we then propose weighted adaptation (W-adapt) to suppress the interference of private classes and reinforce the positive effects of common classes. In particular, we propose a pseudo category margin (PCM) to quantify class importance based on dynamic pseudotarget label prediction to recognize common classes. Furthermore, to alleviate the impact of inaccurate pseudotarget labels, we propose a temporary memory-based filter (TMF) to dynamically store and update the PCM during progressive training. On the basis of the learned TMF, we design a weighted classwise domain alignment loss to adapt two domains across common classes. Experiments on four universal scenarios (i.e., partial-set, open-partial-set, open-set, and closed-set) show that W-adapt outperforms several domain adaptation methods.

Thermodynamic Driving Forces for the Self-Assembly of Diblock Polypeptoids.

Peptoid polymers with sequence-defined side chains are observed to self-assemble into a variety of structures spanning nanometer and micron scales. We explored a diblock copolypeptoid, poly(N-decylglycine)10-block-poly(N-2-(2-(2-methoxyethoxy)ethoxy)-ethylglycine)10 (abbreviated as Ndc10-Nte10), which forms crystalline nanofibers and nanosheets as evidenced by recent cryo-transmission electron microscopy, atomic force microscopy, X-ray diffraction, and calorimetry. Using all-atom molecular dynamics simulations, we examined the thermodynamic forces driving such self-assembly and how nanoscale morphology is tailored through modification of the N-terminus or via the addition of small molecules (urea). We have found that the hydrophobic Ndc domain alignment is key to the formation of molecular stacks whose growth is limited by electrostatic repulsion between protonated N-termini. These stacks are the building blocks that assemble via cooperative van der Waals attraction between the tips of extended decyl side chains to form nanofibers or nanosheets with a well-converged intermolecular interaction energy. Assemblies are significantly more stable in urea solution due to its strong attraction to the peptoid-solvent interface. Isolated peptoids exhibit curved all-cis backbones, which straighten within molecular stacks to maximize contact and registry between neighboring molecules. We hypothesize that competition between this attractive interaction and a strain cost for straightening the backbone is what leads to finite stack widths that define crystalline nanofibers of protonated Ndc10-Nte10. Growth is proposed to proceed through backbone unfurling via trans defects, which is more prevalent in aqueous solution than in THF, indicating a possible pathway to self-assembly under experimentally defined synthesis conditions (viz., THF evaporation).

Integrating human expertise & automated methods for a dynamic and multi-parametric evaluation of large language models’ feasibility in clinical decision-making

BackgroundRecent enhancements in Large Language Models (LLMs) such as ChatGPT have exponentially increased user adoption. These models are accessible on mobile devices and support multimodal interactions, including conversations, code generation, and patient image uploads, broadening their utility in providing healthcare professionals with real-time support for clinical decision-making. Nevertheless, many authors have highlighted serious risks that may arise from the adoption of LLMs, principally related to safety and alignment with ethical guidelines. ObjectiveTo address these challenges, we introduce a novel methodological approach designed to assess the specific feasibility of adopting LLMs within a healthcare area, with a focus on clinical nursing, evaluating their performance and thereby directing their choice. Emphasizing LLMs’ adherence to scientific advancements, this approach prioritizes safety and care personalization, according to the “Organization for Economic Co-operation and Development” frameworks for responsible AI. Moreover, its dynamic nature is designed to adapt to future evolutions of LLMs. MethodThrough integrating advanced multidisciplinary knowledge, including Nursing Informatics, and aided by a prospective literature review, seven key domains and specific evaluation items were identified as follows:1.State of the Art Alignment & Safety.2.Focus, Accuracy & Management of Prompt Ambiguity.3.Data Integrity, Data Security, Ethics & Sustainability, in accordance with OECD Recommendations for Responsible AI.4.Temporal Variability of Responses (Consistency)5.Adaptation to specific standardized terminology and Classifications for healthcare professionals.6.General Capabilities: Post User Feedback Self-Evolution Capability and Organization in Chapters.7.Ability to Drive Evolution in Healthcare.A Peer Review by experts in Nursing and AI was performed, ensuring scientific rigor and breadth of insights for an essential, reproducible, and coherent methodological approach. By means of a 7-point Likert scale, thresholds are defined in order to classify LLMs as “unusable”, “usable with high caution”, and “recommended” categories.Nine state of the art LLMs were evaluated using this methodology in clinical oncology nursing decision-making, producing preliminary results. Gemini Advanced, Anthropic Claude 3 and ChatGPT 4 achieved the minimum score of the State of the Art Alignment & Safety domain for classification as “recommended”, being also endorsed across all domains. LLAMA 3 70B and ChatGPT 3.5 were classified as “usable with high caution.” Others were classified as unusable in this domain. ConclusionThe identification of a recommended LLM for a specific healthcare area, combined with its critical, prudent, and integrative use, can support healthcare professionals in decision-making processes.

Distance-guided domain adaptation for bearing fault diagnosis under variable operating conditions

Transfer learning (TL) has demonstrated effective application in diagnosing bearing faults under varying operating conditions. The current TL methods achieve domain alignment by minimizing the variation in the marginal distribution of data between the source and target domains in the feature space. However, this approach yields incomplete similarity, leading to domain shift and a decrease in diagnostic performance. To overcome this problem, this paper proposes a new distance-guided domain adaptation method that consists of two modules: deep domain adaptive correlation alignment (Deep CORAL) combined with joint maximum mean discrepancy (JMMD) for guided domain adaptation. Deep CORAL employs nonlinear transformations to synchronize second-order statistical correlations across source and target domains, thus ensuring feature-level alignment between these domains. JMMD is utilized to align the joint distribution of input features and output labels within the activation layer in the deep network, thereby bolstering domain alignment. Building on this, we propose a network structure that merges ResNet and bidirectional long short-term memory, powered by wavelet kernels, serving as a feature extractor. This structure is designed to learn domain-invariant features and incorporates attention mechanisms to amplify important information while diminishing the impact of redundant data. An analysis of bearing experiments is used to demonstrate the effectiveness of this method, and the proposed method significantly outperforms several popular methods in diagnostic performance.

HCA-DAN: hierarchical class-aware domain adaptive network for gastric tumor segmentation in 3D CT images

BackgroundAccurate segmentation of gastric tumors from CT scans provides useful image information for guiding the diagnosis and treatment of gastric cancer. However, automated gastric tumor segmentation from 3D CT images faces several challenges. The large variation of anisotropic spatial resolution limits the ability of 3D convolutional neural networks (CNNs) to learn features from different views. The background texture of gastric tumor is complex, and its size, shape and intensity distribution are highly variable, which makes it more difficult for deep learning methods to capture the boundary. In particular, while multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity.MethodsIn this study, we propose a new cross-center 3D tumor segmentation method named Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale context features from the CT images with anisotropic resolution, and a hierarchical class-aware domain alignment (HCADA) module for adaptively aligning multi-scale context features across two domains by integrating a class attention map with class-specific information. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers and validate its segmentation performance in both in-center and cross-center test scenarios.ResultsOur baseline segmentation network (i.e., AsTr) achieves best results compared to other 3D segmentation models, with a mean dice similarity coefficient (DSC) of 59.26%, 55.97%, 48.83% and 67.28% in four in-center test tasks, and with a DSC of 56.42%, 55.94%, 46.54% and 60.62% in four cross-center test tasks. In addition, the proposed cross-center segmentation network (i.e., HCA-DAN) obtains excellent results compared to other unsupervised domain adaptation methods, with a DSC of 58.36%, 56.72%, 49.25%, and 62.20% in four cross-center test tasks.ConclusionsComprehensive experimental results demonstrate that the proposed method outperforms compared methods on this multi-center database and is promising for routine clinical workflows.

Active Dynamic Weighting for multi-domain adaptation

Multi-source unsupervised domain adaptation aims to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Existing methods either seek a mixture of distributions across various domains or combine multiple single-source models for weighted fusion in the decision process, with little insight into the distributional discrepancy between different source domains and the target domain. Considering the discrepancies in global and local feature distributions between different domains and the complexity of obtaining category boundaries across domains, this paper proposes a novel Active Dynamic Weighting (ADW) for multi-source domain adaptation. Specifically, to effectively utilize the locally advantageous features in the source domains, ADW designs a multi-source dynamic adjustment mechanism during the training process to dynamically control the degree of feature alignment between each source and target domain in the training batch. In addition, to ensure the cross-domain categories can be distinguished, ADW devises a dynamic boundary loss to guide the model to focus on the hard samples near the decision boundary, which enhances the clarity of the decision boundary and improves the model’s classification ability. Meanwhile, ADW applies active learning to multi-source unsupervised domain adaptation for the first time, guided by dynamic boundary loss, proposes an efficient importance sampling strategy to select target domain hard samples to annotate at a minimal annotation budget, integrates it into the training process, and further refines the domain alignment at the category level. Experiments on various benchmark datasets consistently demonstrate the superiority of our method.

Remaining useful life prediction under variable operating conditions via multisource adversarial domain adaptation networks

Domain adaptation (DA) methods have been extensively applied for intelligent remaining useful life prediction (RUL) tasks, addressing domain shift issues under variable operating conditions. Almost all existing methods focus on exploiting the single-source unsupervised domain adaptation (SUDA) approach which only learns prognostic knowledge from a single domain. Nevertheless, SUDA methods have significant limitations due to the disregard for the valuable information contained in historical data from numerous sources. Compared to conventional SUDA approaches, multisource unsupervised domain adaptation (MUDA) approaches can acquire invariant domain representation from a variety of sources and offer higher generalization in transfer tasks. Therefore, a novel MUDA framework multisource adversarial domain adaptation network (MADAN) is proposed for regression tasks. MADAN can efficiently organize and utilize multiple source domain data through a two-stage adversarial domain alignment, of which adversarial domain distribution alignment and inter-domain regression alignment modules are designed to minimize domain discrepancy and regressor discrepancy between each pair of source and target domains. Experimental results indicate that MADAN achieves accurate cross-domain predictions by using multiple source domains, and a comparison demonstrates that it performs better than the state-of-the-art approaches.

Maximum open-set entropy optimization via uncertainty measure for universal domain adaptation

Universal Domain Adaptation (UniDA) is a technology that enables the intelligent model to transfer knowledge learned from labeled source domains to related but unlabeled target domains without any prior label set relationship. The key to UniDA lies in rejecting target domain-specific “unknown” samples to achieve domain alignment on shared classes. In this paper, we propose the Maximum Open-set Entropy Optimization via uncertainty measure to adaptively reject “unknown” samples. Specifically, MOEO sets a transition region within the most easily confused class in the open-set space. We optimize the maximum open-set entropy of simple samples outside the transition region to further improve their confidence and separate difficult samples within the transition region by aggregating similar neighbors. Accordingly, a secure boundary is formed between shared samples and “unknown” samples, promoting domain alignment within shared classes. Experiments on four benchmarks show that MOEO outperforms the previous state-of-the-art significantly.

Novel strategies for low-voltage NAND flash memory with negative capacitance effect

Here, we present a novel approach to employing a negative capacitance (NC) phenomenon in the blocking oxide of charge trap flash (CTF) memory. To achieve this, we developed an inversible mono-domain like ferroelectric (IMFE) film through high-pressure post-deposition annealing in a forming gas at 200 atm (FG-HPPDA). The FG-HPPDA process enables to form a uniform alignment of domains and facilitates invertible domain switching behavior in ferroelectrics, generating an internal field by the flexo-electric effect as well as interface-pinned polarization by chemical reaction. Subsequently, to stabilize the NC effect, we fabricated the IMFE/Al2O3 heterostructure, which exhibits an outstanding capacitance-boosting feature. Finally, we successfully demonstrate unprecedented CTF memory with the NC effect in a blocking oxide. Our unique CTF device shows the improved performance (maximum incremental-step-pulse-programming (ISPP) slope ∼1.05) and a large MW (>8 V), attributed to the capacitance boosting by NC phenomenon.

Cross-Scene Hyperspectral Image Classification Based on Graph Alignment and Distribution Alignment

A domain alignment-based hyperspectral image (HSI) classification method was designed to address the heterogeneity in resolution and band between the source domain and target domain datasets of cross-scene hyperspectral images, as well as the resulting reduction in common features. Firstly, after preliminary feature extraction, perform two domain alignment operations: image alignment and distribution alignment. Image alignment aims to align hyperspectral images of different bands or time points, ensuring that they are within the same spatial reference framework. Distribution alignment adjusts the distribution of features of samples of different categories in the feature space to reduce the distribution differences of the same type of features between two domains. Secondly, adjust the consistency of the two alignment methods to ensure that the features obtained through different alignment methods exhibit consistency in the feature space, thereby improving the comparability and reliability of the features. In addition, this method considers multiple losses in the model from different perspectives and makes comprehensive adjustments through a unified optimization process to more comprehensively capture and utilize the correlation information between data. Experimental results on Houston 2013 and Houston 2018 datasets can improve the hyperspectral prediction performance between datasets with different resolutions and bands, effectively solving the problems of high cost and limited training samples in HSI labeling and significantly improving cross-scene HSI classification performance.

POST: Prototype‐oriented similarity transfer framework for cross‐domain facial expression recognition

AbstractFacial expression recognition (FER) is one of the popular research topics in computer vision. Most deep learning expression recognition methods perform well on a single dataset, but may struggle in cross‐domain FER applications when applied to different datasets. FER under cross‐dataset also suffers from difficulties such as feature distribution deviation and discriminator degradation. To address these issues, we propose a prototype‐oriented similarity transfer framework (POST) for cross‐domain FER. The bidirectional cross‐attention Swin Transformer (BCS Transformer) module is designed to aggregate local facial feature similarities across different domains, enabling the extraction of relevant cross‐domain features. The dual learnable category prototypes is designed to represent potential space samples for both source and target domains, ensuring enhanced domain alignment by leveraging both cross‐domain and specific domain features. We further introduce the self‐training resampling (STR) strategy to enhance similarity transfer. The experimental results with the RAF‐DB dataset as the source domain and the CK+, FER2013, JAFFE and SFEW 2.0 datasets as the target domains, show that our approach achieves much higher performance than the state‐of‐the‐art cross‐domain FER methods.

Water Hydrogen-Bond Mediated Layer by Layer Alignment of Lipid Rafts as a Precursor of Intermembrane Processes.

Lipid rafts, which are dynamic nanodomains in the plasma membrane, play a crucial role in intermembrane processes by clustering together and growing in size within the plane of the membrane while also aligning with each other across different membranes. However, the physical origin of layer by layer alignment of lipid rafts remains to be elucidated. Here, by using fluorescence imaging and synchrotron X-ray reflectivity in a phase-separated multilayer system, we find that the alignment of raft-mimicking Lo domains is regulated by the distance between bilayers. Molecular dynamics simulations reveal that the aligned state is energetically preferred when the intermembrane distance is small due to its ability to minimize the volume of surface water, which has fewer water hydrogen bonds (HBs) compared to bulk water. Our results suggest that water HB-driven alignment of lipid rafts plays a role as a precursor of intermembrane processes such as cell-cell fusion, virus entry, and signaling.