Tag: Few-shot learning

A modeling study found that MAML-GPR predicted TiN coating thickness more accurately than four reference models under fivefold cross-validation and ...

Researchers at Sun Yat-sen University have developed an improved convolutional prototype network that classifies known environmental sounds and rejects unknown ...

A new incremental few-shot fault diagnosis framework uses a diffusion model to generate synthetic samples for rare new fault classes, ...

Researchers have built a temporal-aware retrieval-augmented generation framework that helps large language models generate safer, evidence-based treatment plans for idiopathic ...

A new few-shot learning framework called ViTRelNet co-adapts a fine-tuned Vision Transformer with a learned similarity metric to classify unseen ...

A systematic review of 91 studies shows AI-based medication recognition advancing rapidly through detection, OCR, and few-shot learning, while external ...

Egyptian researchers have built a hybrid Vision Transformer and CNN framework with spectral band selection that outperforms few-shot learning methods ...

A new frequency-aware study reveals that oracle bone character detectors scoring well overall nearly fail on rare glyphs, and introduces ...

Researchers have developed a few-shot AI framework that combines agentic retrieval-augmented generation with multi-agent data augmentation to detect coded dog-whistle ...

Researchers have combined prototypical few-shot learning with adversarial training to build an IoT intrusion detection system that learns attacks from ...