Results 131 to 140 of about 4,930,132 (374)

SDCL: Self-Distillation Contrastive Learning for Chinese Spell Checking

, 2022
Due to the ambiguity of homophones, Chinese Spell Checking (CSC) has widespread applications. Existing systems typically utilize BERT for text encoding. However, CSC requires the model to account for both phonetic and graphemic information. To adapt BERT
Qiu, Xipeng, Sun, Yu, Yan, Hang, Zhang, Xiaotian   +3 more
core  

The Floor‐Ceiling‐Chip, or 2 × 2D = Pseudo‐3D—Approaching 3D Cell Morphology and Organization between Two Opposing 2D Substrates with Cell‐Adhesive Protein Micropatterns

Advanced Healthcare Materials, EarlyView.
Here, we present a novel 3D cell patterning and culture platform. The “Floor‐Ceiling‐Chip” (FC‐Chip) consists of two opposing track‐etched membranes, creating a pseudo‐3D microenvironment for the cells in between. By providing the membranes with micropatterned cell‐adhesive islands of varying geometries and sizes, the FC‐Chip enables control over cell ...
Urandelger Tuvshindorj, Francesca Giacomini, Esra Güben Kaçmaz, Tim ten Brink, Lorenzo Moroni, Zeinab Tahmasebi Birgani, Clemens van Blitterswijk, Pamela Habibović, Stefan Giselbrecht, Jan de Boer, Roman Truckenmüller   +10 more
wiley   +1 more source

Vision Transformers with Self-Distilled Registers

NeurIPS 2025 Spotlight.
Chen, Yinjie, Yan, Zipeng, Zhou, Chong, Dai, Bo, Luo, Andrew F.   +4 more
openaire   +2 more sources

High‐Throughput Generation of Tumor Spheroids via Droplet Microfluidics for siRNA‐Loaded Nanomedicine Assessment

Advanced Healthcare Materials, EarlyView.
A droplet microfluidic platform is employed to enable high‐throughput, uniform tumor spheroid generation for evaluating siRNA‐loaded nanomedicines at the protein level. As a proof of concept, breast (MCF‐7) and brain (U87 MG) cancer cell lines are investigated using this platform, revealing penetration profiles and therapeutic responses between the two
Ling Liu, Guoying Wang, Yang Zhang, Bingyang Shi, Ming Li   +4 more
wiley   +1 more source

A Lightweight Network With Embedded Soft Constraints on Approximate Spectral Features for Real-Time Water Body Segmentation in Remote Sensing Images

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Real-time extraction of water bodies from remote sensing images captured by unmanned aerial vehicles (UAVs) or satellites is challenging due to the difficulty in performing precise atmospheric correction and other preprocessing steps. In this article, we
Qingqing Cao, Boya Zhao, Zijin Li, Fangfang Zhang, Yuanfeng Wu   +4 more
doaj   +1 more source

MSSD: multi-scale self-distillation for object detection

Visual Intelligence
Knowledge distillation techniques have been widely used in the field of deep learning, usually by extracting valid information from a neural network with a large number of parameters and a high learning capacity (the teacher model) to a neural network ...
Zihao Jia, Shengkun Sun, Guangcan Liu, Bo Liu   +3 more
semanticscholar   +1 more source

Learn More for Food Recognition via Progressive Self-Distillation

, 2023
Food recognition has a wide range of applications, such as health-aware recommendation and self-service restaurants. Most previous methods of food recognition firstly locate informative regions in some weakly-supervised manners and then aggregate their ...
Liu, Linhu, Tian, Jiang, Zhu, Yaohui
core  

Coacervates Made of Elastin‐Like Polypeptides Fused with Melanocyte‐Stimulating Hormone and Monocyte Chemoattractant Protein Enhance Skin Wound Healing in Spinal Cord‐Injured Mice

Advanced Healthcare Materials, EarlyView.
Pressure skin wounds are frequent complications after spinal cord injury (SCI), with impaired healing due to vascular and immune deficits. Elastin‐like polypeptides (ELP) fused to α‐MSH (MSH‐ELP) or MCP‐1 (MCP‐ELP) are developed and tested on these wounds. The resulting nanoparticles are non‐toxic and bioactive, and they enhance macrophage recruitment,
Suneel Kumar, Dhruv Patel, Greeshma Manjunath, Shashank Madhavan, Ashley Mathew, Dnyaneshwari Rananavare, Jahnavi Shah, Francois Berthiaume   +7 more
wiley   +1 more source

A Novel Multibranch Self-Distillation Framework for Optimizing Remote Sensing Change Detection

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning (DL) has achieved remarkable success in the field of change detection (CD) for remote sensing images. Existing training methods for DL-based CD models are predominantly single-stage, single-stream, and end-to-end.
Ziyuan Liu, Jiawei Zhang, Wenyu Wang, Yuantao Gu   +3 more
doaj   +1 more source

CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation [PDF]

, 2023
Wenxuan Wang, Jing Liu, Xingjian He, Yisi Zhang, Chen Chen, Jiachen Shen, Yan Zhang, Jiangyun Li   +7 more
openalex   +1 more source