GLiNER-BioMed: a suite of efficient models for open biomedical named entity recognition. [PDF]
BioinformaticsYazdani A, Stepanov I, Teodoro D.
europepmc +1 more source
Stabilizing Extreme Few-Shot ECG Classification via Self-Supervised Contrastive Pretraining. [PDF]
Ann Noninvasive ElectrocardiolZeng L, Pan J, Lu Y, Pan X.
europepmc +1 more source
MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics. [PDF]
BioinformaticsCui B +6 more
europepmc +1 more source
mmContext: an open framework for multimodal contrastive learning of omics and text data. [PDF]
BioinformaticsMenger J +4 more
europepmc +1 more source
An integrated evolution-aware meta-learning framework with adversarial morphological augmentation for zero-day threat detections. [PDF]
Front Artif IntellLanka K, Shaik K.
europepmc +1 more source
InfoMSD: an information-maximization self-distillation framework for parameter-efficient fine-tuning on artwork images. [PDF]
Front Artif IntellGuan F, Hong H, Wang Y.
europepmc +1 more source
Related searches:
Zero-Shot Turkish Text Classification
2021 29th Signal Processing and Communications Applications Conference (SIU), 2021The method frequently used for text classification is supervised modeling with a large training set with labels. In some cases, we may not have labeled data. Modeling in the absence of labeled data for target classes is called zero-shot modeling. For zero-shot text classification natural language inference is utilized which is another branch of natural
Ahmet Birim +2 more
exaly +3 more sources
Prototype adjustment for zero shot classification
Signal Processing: Image Communication, 2019Abstract Zero shot classification addresses the problem of classifying unseen classes with seen class samples. Current zero shot learning methods mostly focus on learning the mapping function from image feature space to semantic space which is extremely important. However, these methods assume the seen and unseen class prototypes are fixed.
Min Fang, Haikun Li
exaly +2 more sources
Zero-shot classification with unseen prototype learning
Neural Computing and Applications, 2021Zero-shot learning (ZSL) aims at recognizing instances from unseen classes via training a classification model with only seen data. Most existing approaches easily suffer from the classification bias from unseen to seen categories since the models are only trained with seen data.
Zhong Ji +4 more
openaire +2 more sources
Zero-shot image classification based on attribute
2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), 2017In the image classification task, traditional model can only recognize annotated image samples, but class labels can't involve all the object categories. In order to reduce the dependence on the labels and recognize unannotated object samples, this paper proposes zero-shot image classification based on attribute.
Wei Zhang +3 more
openaire +2 more sources