Repository navigation
fewshot-learning
- Website
- Wikipedia
EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit
Kernel Fisher Discriminant Analysis implementation following https://arxiv.org/abs/1906.09436
Codes for "Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier"
Meta Transfer Learning for Few Shot Semantic Segmentation using U-Net
Example of one shot learning and few shot learning with omniglot dataset.
[CVPR 2025] Few-shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
根据关键词从Openaccess网站获取文章列表，CVPR2020/WACV2020小样本论文合辑
Interactive Skeleton Based Few Shot Action Recognition
Source code of NeurIPS 2021 paper “Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media”
Testing code for few-shot action recognition
[ICASSP2025] Cross-Domain Few-Shot Open-Set Keyword Spotting Using Keyword Adaptation and Prototype Reprojection
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models TensorFlow
ACDFSL for Hyperspectral Image Classification
MAML implementation in PyTorch.
The repository hosts the code, data, and other artefacts for the paper "A deep learning-based approach for identifying unresolved questions on Stack Exchange Q&A communities through graph-based communication modelling", available here: https://link.springer.com/article/10.1007/s41060-023-00454-0
A PyTorch implementation of paper "PFENet: Prior Guided Feature Enrichment Network for Few-shot Segmentation".
Este repositório é um tutorial completo e prático que explora metodologias avançadas para a classificação de sentimentos e emoções em textos, utilizando Modelos de Linguagem de Grande Porte (LLMs). O projeto foi desenvolvido para ser acessível, com todos os exemplos executáveis em ambientes gratuitos como o Google Colab.
Scripts, algorithms and files for a rule-based and ML-based approach for binary classification of regulatory / non-regulatory sentences in EU legislative documents, as well as code for evaluating the accuracy of these approaches
Code for Continual Few-Shot Learning for the submission to the Nagasaki Internship program