Results 151 to 160 of about 4,930,132 (374)

Decoupled Time-Dimensional Progressive Self-Distillation With Knowledge Calibration for Edge Computing-Enabled AIoT

open access: yesIEEE Access
The time-dimensional self-distillation seeks to transfer knowledge from earlier historical models to subsequent ones with minimal computational overhead.
Yingchao Wang, Wenqi Niu, Hanpo Hou
doaj   +1 more source

Macrophage Membrane‐Cloaked, ROS‐Triggered Quercetin Nanocarriers Target Ovarian Lesions to Treat Polycystic Ovary Syndrome

open access: yesAdvanced Healthcare Materials, EarlyView.
The synthesis process of MM@PCD@QNPs and its potential mechanism for treating PCOS. (A) Assembly steps of MM@PCD@QNPs. (B) Synthesis and decomposition of MM@PCD@QNPs. (C) Potential therapeutic mechanisms of MM@PCD@QNPs for PCOS. PCD, PABP conjugated with DEX polymer; QUR, quercetin; CDI, N, N′‐carbonyldiimidazole; DEX, dextran; PABP, 4‐(hydroxymethyl ...
Wenzhu Li   +9 more
wiley   +1 more source

Injectable Stimuli‐Responsive Amphiphilic Hydrogel for Rapid Hemostasis, Robust Tissue Adhesion, and Controlled Drug Delivery in Trauma and Surgical Care

open access: yesAdvanced Healthcare Materials, EarlyView.
Fast‐acting hydrogel seals bleeding wounds as the illustrated injectable, pH‐responsive network rapidly gels in situ to stop hemorrhage, adhere strongly to wet tissue, and release antibiotics in a controlled, pH‐dependent manner. The material withstands high pressures, shows excellent biocompatibility, and degrades safely, offering a versatile platform
Arvind K. Singh Chandel   +5 more
wiley   +1 more source

SDLS: A Two-Stream Architecture with Self-Distillation and Local Streams for Remote Sensing Image Scene Classification

open access: yesRemote Sensing
Remote sensing image scene classification holds significant application value and has long been a research hotspot in remote sensing. However, remote sensing images contain diverse objects and complex backgrounds.
Xinliang Ma   +4 more
doaj   +1 more source

An In Situ Embedded B‐MOF Sponge With Shape‐Memory for All‐in‐One Diabetic Wound Therapy

open access: yesAdvanced Healthcare Materials, EarlyView.
A smart shape‐memory sponge dressing (P1A3@B‐MOF) is developed for accelerated diabetic wound healing. It achieves pH‐responsive corelease of Zn2+ and salvianolic acid B, synergistically providing antibacterial action, repolarizing macrophages to the M2 phenotype, and promoting angiogenesis.
Hai Zhou   +11 more
wiley   +1 more source

Online Prototype Angular Balanced Self-Distillation for Non-Ideal Annotation in Remote Sensing Image Segmentation

open access: yesRemote Sensing
This paper proposes an Online Prototype Angular Balanced Self-Distillation (OPAB) framework to address the challenges posed by non-ideal annotation in remote sensing image semantic segmentation.
Hailun Liang   +4 more
doaj   +1 more source

M2SD: Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning

open access: yesAAAI Conference on Artificial Intelligence
Few-shot Class-incremental learning (FSCIL) is a challenging task in machine learning that aims to recognize new classes from a limited number of instances while preserving the ability to classify previously learned classes without retraining the entire ...
Jinhao Lin   +4 more
semanticscholar   +1 more source

A Tri‐Culture Heart‐on‐a‐Chip Platform With iPSC‐Derived Cardiac Cells for Predictive Cardiotoxicity Testing

open access: yesAdvanced Healthcare Materials, EarlyView.
This study presents the first entirely isogenic heart‐on‐chip, unifying cardiomyocytes, fibroblasts, and endothelial cells from a single iPSC source. The platform reveals a critical biological insight: the endothelium actively shields cardiac tissue from drug‐induced toxicity, challenging the predictive accuracy of conventional, avascular models for ...
Karine Tadevosyan   +12 more
wiley   +1 more source

Class-Aware Self-Distillation for Remote Sensing Image Scene Classification

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Currently, convolutional neural networks (CNNs) and vision transformers (ViTs) are widely adopted as the predominant neural network architectures for remote sensing image scene classification.
Bin Wu, Siyuan Hao, Wei Wang
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy