Results 161 to 170 of about 8,068,927 (352)

Pseudo-Labeling Domain Adaptation Using Multi-Model Learning

open access: yesIEEE Access
With the constant growth of state-of-the-art models, obtaining sufficient labeled data to train these models for specific domains has become increasingly costly.
Victor Akihito Kamada Tomita   +1 more
doaj   +1 more source

Domain Adaptation for Dependency Parsing at Evalita 2011

open access: yes, 2012
The domain adaptation task was aimed at investigating techniques for adapting state-of-the-art dependency parsing systems to new domains. Both the language dealt with, i.e.
Dell'Orletta Felice   +5 more
core  

ALFREDO: Active Learning with FeatuRe disEntangelement and DOmain adaptation for medical image classification. [PDF]

open access: yes
State-of-the-art deep learning models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data.
Tennakoon, Ruwan   +13 more
core   +1 more source

Hijacking emergency granulopoiesis: Neutrophil ontogeny and reprogramming in cancer

open access: yesMolecular Oncology, EarlyView.
Neutrophils are highly plastic innate immune cells; their functions in cancer extend beyond the tumour microenvironment. This Review summarises current understanding of neutrophil maturation and heterogeneity and highlights tumour‐induced granulopoiesis as a systemic programme that expands immature, immunosuppressive neutrophils via tumour‐derived ...
Gabriela Marinescu, Yi Feng
wiley   +1 more source

Dynamic Target Distribution Estimation for Source-Free Open-Set Domain Adaptation

open access: yes
Unsupervised domain adaptation (UDA) has emerged as a promising technique for transferring knowledge from a labeled domain to an unlabeled domain. However, existing UDA methods are severely constrained by data privacy and semantic inconsistencies.
Chen, Zhi   +4 more
core   +1 more source

Cancer‐associated mutations in endometriosis reframe a benign disease through molecular oncology

open access: yesMolecular Oncology, EarlyView.
This review aims to comprehensively analyse cancer‐associated somatic mutations (CAMs) present in endometriotic lesions, emphasizing their biological roles, spatial distribution and implications for translational applications in medicine. By contextualizing a benign state within a genomic framework, this analysis seeks to establish its value as a ...
Clarissa Mujacic   +15 more
wiley   +1 more source

Somatostatin receptor 4 (SSTR4) is a tumor suppressor in cutaneous and head & neck squamous cell carcinomas

open access: yesMolecular Oncology, EarlyView.
This study identifies somatostatin receptor 4 (Sstr4) as a critical tumor suppressor against skin and head/neck cancers (HNSCC, cSCC, and BCC). The loss of Sstr4 removes a check on cell growth, causing hyperactivation of the MAPK‐ERK signaling pathway (↑).
Ali Taqvi   +6 more
wiley   +1 more source

Partial FAK suppression promotes tumor growth, an effect reversed by macrophage p110δ PI3K inactivation

open access: yesMolecular Oncology, EarlyView.
Partial inhibition of focal adhesion kinase (FAK) can paradoxically promote tumor growth, rather than simply producing a weaker antitumor effect than that observed with strong FAK suppression. In breast cancer and melanoma models, targeting p110δ PI3K, particularly in macrophages, counteracted these tumor‐promoting effects, highlighting the importance ...
Lydia Xenou   +4 more
wiley   +1 more source

Mechanisms and therapeutic opportunities of the ribotoxic stress response in cancer

open access: yesMolecular Oncology, EarlyView.
Cancer cells' high translational demand creates opportunities to therapeutically target ribosome function. Ribosome stalling and collisions activate ZAKα and the ribotoxic stress response (RSR), which can trigger rapid, p53‐independent apoptosis in cancer.
Anastassiya Kim   +7 more
wiley   +1 more source

Fairness across domains: a unified fairness-aware framework for domain generalization and unsupervised adaptation

open access: yesFrontiers in Big Data
Fairness in machine learning remains a critical challenge, particularly in the presence of domain shift. We propose a unified fairness-aware framework for both domain generalization (DG) and unsupervised domain adaptation (UDA), which jointly addresses ...
Kai Jiang   +6 more
doaj   +1 more source

Home - About - Disclaimer - Privacy