Boyu Wang
YOU?
Author Swipe
View article: Preventive value of systematic nursing for lower limb deep venous thrombosis after obstetrics and gynaecology surgery
Preventive value of systematic nursing for lower limb deep venous thrombosis after obstetrics and gynaecology surgery Open
Objective: To clarify the impact of systematic nursing on preventing lower limb deep venous thrombosis after obstetricsand gynaecology surgery.Method: The study was conducted at the Nanjing Women and Children's Healthcare Hospital, Nanjing…
View article: Class-Missing Semi-supervised document key information extraction via synergistic refinement estimation
Class-Missing Semi-supervised document key information extraction via synergistic refinement estimation Open
View article: A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling
A deep active learning framework for mitotic figure detection with minimal manual annotation and labelling Open
Aims Accurately and efficiently identifying mitotic figures (MFs) is crucial for diagnosing and grading various cancers, including glioblastoma (GBM), a highly aggressive brain tumour requiring precise and timely intervention. Traditional …
View article: Homophily Enhanced Graph Domain Adaptation
Homophily Enhanced Graph Domain Adaptation Open
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. In this paper, we highlight the significance of graph homophily, a pivotal factor for grap…
View article: The Impact of Cardiometabolic Index on Cardiovascular Disease Risk Among Diabetic Patients: Evidence From Two National Cohorts
The Impact of Cardiometabolic Index on Cardiovascular Disease Risk Among Diabetic Patients: Evidence From Two National Cohorts Open
Background This study investigates the relationship between the Cardiometabolic Index (CMI) and cardiovascular disease (CVD) risk in diabetic populations using data from the National Health and Nutrition Examination Survey (NHANES) and the…
View article: ConFREE: Conflict-free Client Update Aggregation for Personalized Federated Learning
ConFREE: Conflict-free Client Update Aggregation for Personalized Federated Learning Open
Negative transfer (NF) is a critical challenge in personalized federated learning (pFL). Existing methods primarily focus on adapting local data distribution on the client side, which can only resist NF, rather than avoid NF itself. To tac…
View article: Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning
Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning Open
Dense contrastive representation learning (DCRL) has greatly improved the learning efficiency for image dense prediction tasks, showing its great potential to reduce the large costs of medical image collection and dense annotation. However…
View article: Multivariate Pattern Analysis of EEG Reveals Neural Mechanism of Naturalistic Target Processing in Attentional Blink
Multivariate Pattern Analysis of EEG Reveals Neural Mechanism of Naturalistic Target Processing in Attentional Blink Open
The human brain has inherent limitations in consciously processing visual information. When individuals monitor a rapid sequence of images for detecting two targets, they often miss the second target (T2) if it appears within a short time …
View article: Association between cardiometabolic Index (CMI) and endometriosis: a cross-sectional study on NHANES
Association between cardiometabolic Index (CMI) and endometriosis: a cross-sectional study on NHANES Open
View article: Sparse and Expandable Network for Google's Pathways
Sparse and Expandable Network for Google's Pathways Open
Introduction Recently, Google introduced Pathways as its next-generation AI architecture. Pathways must address three critical challenges: learning one general model for several continuous tasks, ensuring tasks can leverage each other with…
View article: Unveiling the neural dynamics of conscious perception in rapid object recognition
Unveiling the neural dynamics of conscious perception in rapid object recognition Open
Our brain excels at recognizing objects, even when they flash by in a rapid sequence. However, the neural processes determining whether a target image in a rapid sequence can be recognized or not remains elusive. We used electroencephalogr…
View article: PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter Open
This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs hav…
View article: Decentralized Federated Learning: A Survey on Security and Privacy
Decentralized Federated Learning: A Survey on Security and Privacy Open
Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages. Nevertheless, the exchange of model updates and gradients in this architecture provides new…
View article: Deep learning system for true- and pseudo-invasion in colorectal polyps
Deep learning system for true- and pseudo-invasion in colorectal polyps Open
View article: Source-Free Domain Adaptation for Question Answering with Masked Self-training
Source-Free Domain Adaptation for Question Answering with Masked Self-training Open
Previous unsupervised domain adaptation (UDA) methods for question answering (QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and sh…
View article: Toward Open-ended Embodied Tasks Solving
Toward Open-ended Embodied Tasks Solving Open
Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years. A major challenge is task open-endedness. In practice, robots often need to perform tasks with novel goals tha…
View article: Multivariate Pattern Analysis of EEG Reveals Neural Mechanism of Naturalistic Target Processing in Attentional Blink
Multivariate Pattern Analysis of EEG Reveals Neural Mechanism of Naturalistic Target Processing in Attentional Blink Open
The human brain has inherent limitations in consciously processing visual information. When individuals monitor a rapid sequence of images for detecting two targets, they often miss the second target (T2) if it appears within a short time …
View article: Unveiling the neural dynamics of conscious perception in rapid object recognition
Unveiling the neural dynamics of conscious perception in rapid object recognition Open
Our brain excels at recognizing objects, even when they flash by in a rapid sequence. However, the neural processes determining whether a target image in a rapid sequence can be recognized or not remained elusive. We used electroencephalog…
View article: Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimization
Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimization Open
Vertical Federated Learning (VFL) attracts increasing attention because it empowers multiple parties to jointly train a privacy-preserving model over vertically partitioned data. Recent research has shown that applying zeroth-order optimiz…
View article: Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation Open
Current methods of blended targets domain adaptation (BTDA) usually infer or consider domain label information but underemphasize hybrid categorical feature structures of targets, which yields limited performance, especially under the labe…
View article: Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment Open
Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…
View article: Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation
Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation Open
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial. Existing methods either have low efficiency (e.g., backward optimization) or ig…
View article: Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation
Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation Open
In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial. Existing methods either have low efficiency (e.g., backward optimization) or ig…
View article: Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation Open
Current methods of blended targets domain adaptation (BTDA) usually infer or consider domain label information but underemphasize hybrid categorical feature structures of targets, which yields limited performance, especially under the labe…
View article: When Source-Free Domain Adaptation Meets Learning with Noisy Labels
When Source-Free Domain Adaptation Meets Learning with Noisy Labels Open
Recent state-of-the-art source-free domain adaptation (SFDA) methods have focused on learning meaningful cluster structures in the feature space, which have succeeded in adapting the knowledge from source domain to unlabeled target domain …
View article: Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment Open
Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…
View article: On Learning Fairness and Accuracy on Multiple Subgroups
On Learning Fairness and Accuracy on Multiple Subgroups Open
We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups,…
View article: Evolving Domain Generalization
Evolving Domain Generalization Open
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalization methods ignore …
View article: Fair Representation Learning through Implicit Path Alignment
Fair Representation Learning through Implicit Path Alignment Open
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups. Specifically, we formulate this intuition as a bi-level …
View article: Weakly Supervised Object Localization as Domain Adaption
Weakly Supervised Object Localization as Domain Adaption Open
Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects base…